Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare destructiveHint=true, openWorldHint=true and readOnlyHint=false, yet the description says nothing about what is written, what may be overwritten, or where results go. For a long-running permutation-based analysis (1000 iterations default) it also omits runtime/cost expectations, so the most consequential behaviors are left entirely to the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Short and front-loaded with the purpose, but the pseudo-docstring 'Args:' block wastes a line restating data_id, and the subset_key sentence is dangling after it with no framing. Content is minimal but the ordering is slightly disjointed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the description covers the required inputs plus the most error-prone configuration choices. What remains missing is guidance on spatial vs cluster mode and the destructive/write behavior, but the essentials for invoking it correctly are present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description highlights the required params (species, cell_type_key, method) and adds a genuinely useful dependency rule (mouse + liana → liana_resource='mouseconsensus', subset_key paired with subset_categories). But the params object carries dozens of method-specific knobs that the description never characterizes, and the 'data_id: Dataset ID' line merely restates the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Analyze cell-cell communication and ligand-receptor interaction patterns', which is clearly distinct from siblings like analyze_enrichment or analyze_trajectory_data. However it does not explicitly distinguish itself from analyze_spatial_statistics or note that it can run in both cluster and spatial modes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Offers practical routing hints ('For mouse with liana, set liana_resource=mouseconsensus') and a filtering example, but never says when to choose this tool over alternatives or when to enable/disable spatial analysis. Usage is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare destructiveHint=true and readOnlyHint=false, yet the description never says that the dataset is modified or what results get written (cnv_clusters labels are only mentioned in passing via query_categories). It does add real value on gene-position sourcing from bundled Ensembl 110 tables and on what exclude_gene_classes strips from the input, but the mutation surface remains undisclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One-sentence purpose up front, then a compact Args block, then behavior notes. A few sentences restate schema-level detail (gene_positions source, exclude_gene_classes contents) but nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists and the nested params model is richly annotated, so return values need not be explained. The gap is behavioral: for a destructive, non-read-only operation, the description gives no warning that analysis results are persisted or that re-running may overwrite existing labels.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Top-level schema coverage is 0% (data_id undocumented, params is a bare $ref), so the description must carry weight; it names the required fields and explains gene_positions fallback and query_categories filtering semantics. However, the nested CNVParameters schema already documents most of these in depth, so the description's marginal gain is modest.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — 'Analyze copy number variations (CNVs) in spatial transcriptomics data' — which is unique among the siblings (none of which touch CNV). An agent can distinguish it immediately from find_markers, deconvolve_data, or identify_spatial_domains.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The Args block flags which params are required (reference_key, reference_categories) and which are optional, giving implied preconditions. But it never says when to choose this tool over alternatives, nor when CNV analysis is inappropriate (e.g. no reference labels, no allele data for numbat).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations include destructiveHint=true and idempotentHint=true, but the description provides no additional behavioral context. It does not mention potential side effects, modifications to the dataset, or any safety considerations. While it doesn't contradict annotations, it adds no value beyond what the annotations already convey, leaving the agent uninformed about the tool's actual behavior on data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: a single sentence and two argument placeholders. It avoids redundancy and gets straight to the point. Every word earns its place, though it may be too sparse for a complex tool. However, for conciseness, it is exemplary—no fluff, no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema, the description is minimal and does not explain the overall context of use. It fails to mention the type of data expected, the output interpretation, or any preconditions (e.g., data must be loaded and preprocessed). It also does not relate to the analysis pipeline or when to apply this analysis. For a tool with many configurable parameters and complex behavior, this is incomplete and leaves the agent without sufficient guidance.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides detailed descriptions for most parameters (e.g., method, species, max_genes), and the description adds only a note that species must be specified and points to EnrichmentParameters for details. Given high schema coverage, the description adds marginal value. However, it does highlight the required nature of species, which is helpful, but does not explain semantics beyond that. Baseline of 3 is appropriate as the description slightly supplements the schema but does not compensate for deeper meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool 'Performs gene set enrichment analysis' which is a specific verb and resource. It clearly distinguishes from generic analysis tools but doesn't explicitly differentiate from sibling tools like analyze_spatial_statistics or deconvolve_data, though the enrichment focus is evident. It lacks a clear scope or mention of input/output context, but the core purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives only a minimal usage hint: 'Required - species must be specified.' It does not explain when to use this tool over alternatives, what scenarios it suits, or when not to use it. There is no reference to the relevant analysis workflow or comparison with sibling tools like find_markers or compute_embeddings. This guidance is insufficient for an agent to make an informed selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds meaningful behavioral context by explaining that gene_selection='all' computes Moran/Geary for every gene and stores the full per-gene table at results_key while returning only top genes. This aligns with the destructive/non-readOnly annotations because it discloses that results are written into the data object, though it does not elaborate on permissions or mutation scope.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loads the core purpose before the Args block and the gene_selection note. It wastes little space, though the Args formatting is somewhat redundant with the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity, rich nested parameter schema, and presence of an output schema, the description covers the essential call shape and one important storage/return behavior. It still omits enough about analysis-type selection and cluster_key requirements that an agent must rely heavily on the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The top-level Args block briefly maps data_id to Dataset ID and params to analysis parameters, and points to SpatialStatisticsParameters for the full set. However, most parameter semantics live in the nested schema, which is richly documented, so the description itself adds only marginal meaning beyond the structured definition.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: analyze spatial statistics and autocorrelation patterns. It is clear enough to distinguish this from most sibling tools, but it does not explicitly contrast with closely related tools such as find_spatial_genes or identify_spatial_domains.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage guidance is implied through the parameter model and the note about gene_selection='all', but the description itself does not say when to choose this tool over siblings or when specific analysis types are appropriate. The schema carries much of the routing detail via analysis_type's enum description, leaving the prose only partially helpful.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already communicate readOnlyHint=false and destructiveHint=true, so the risk profile is known. The description adds no side-effect context, such as whether trajectory results overwrite existing data or require prior preprocessing, but it does not contradict the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short, front-loaded, and free of fluff. The args lines add minimal value because the schema already defines the parameters, but overall this is a compact, readable description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a complex trajectory-analysis tool with multiple methods, method-specific parameters, and a destructive hint, but the description only provides a one-line purpose. Important selection context—such as method-specific data requirements and expected inputs—is buried in the nested schema rather than presented in the description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description only lists 'method, root_cell, spatial_weight, etc.' in passing and does not provide meaningful parameter semantics. It also uses 'root_cell' while the schema defines the field as 'root_cells'. The actual parameter understanding relies on the rich nested schema descriptions, not the tool description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The sentence 'Infer cellular trajectories and pseudotime ordering' names a specific analysis task with a clear action and object. It is distinct from most sibling tools, though it does not explicitly contrast with related tools like analyze_velocity_data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance is provided: there are no hints about velocity prerequisites, when to choose palantir/dpt over cellrank, or when another analysis tool would be more appropriate. Some guidance exists only in the nested schema description, not in the tool description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already include destructiveHint=true and readOnlyHint=false, but the description adds no additional behavioral context such as what data might be modified, whether results are stored, or any side effects. The only extra information is the data prerequisite (spliced/unspliced layers), which is more about applicability than behavior. Thus, it contributes minimal value beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded, stating the main purpose in the first sentence. It then lists the arguments in a simple format. It avoids unnecessary fluff but could be slightly more structured, e.g., by using a numbered list or table for the args. Overall, it earns a 4 for economy of words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema and annotations, the description is incomplete for a tool with this complexity. It only names two parameters, while the params parameter contains a large nested object with a dozen fields. There is no guidance on how to choose between methods (scvelo vs velovi), what the output contains, or what happens if certain layers are missing. A more complete description would help an agent correctly configure and invoke the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It provides only terse definitions: 'data_id: Dataset ID' and 'params: Velocity parameters (method, scvelo_mode, etc.)'. While it gives examples of sub-parameters, it does not explain the many nested parameters or how they affect the analysis. The params object is a complex nested model with a dozen properties, and the description adds little meaning beyond what the schema already shows.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Analyze RNA velocity to understand cellular dynamics.' This includes a specific verb ('analyze'), a specific resource ('RNA velocity'), and biological context. It distinguishes itself from sibling tools like analyze_trajectory_data by focusing specifically on RNA velocity, and it mentions the technical prerequisite of needing 'spliced' and 'unspliced' layers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives a clear context for when the tool is applicable by specifying the requirement for 'spliced' and 'unspliced' layers, which is a key prerequisite. However, it does not mention alternative tools or explicitly state when not to use this tool, so it does not fully meet the 'explicit alternatives' criterion.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds meaningful behavioral context: rule-based methods write labels to output_key, reference methods require preprocessed reference data, and marker_score assigns labels in order. However, it does not warn about overwriting existing obs columns or discuss computational cost, even though annotations mark the tool destructive and open-world.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the purpose and then structured into Args and a Note. It is dense but efficient; a few details such as the full method list are left to the schema rather than repeated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex annotation tool with an output schema and destructive annotations, the description covers the main method families, prerequisites, and output-key behavior. It is not fully complete because it omits overwrite warnings and does not explain every method family, but the schema covers many parameter-level details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although the top-level schema lists only data_id and params, the description adds real meaning beyond the schema by summarizing method categories, required reference_data_id, cell_type_key, marker_score/threshold behavior, and output_key. Many nested parameters are left to schema descriptions, but the key decision parameters are explained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: annotate cell types in spatial transcriptomics data. It is clear what the tool does, but it does not explicitly distinguish it from related siblings such as deconvolve_data or identify_spatial_domains.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives useful usage guidance by explaining that reference-based methods tangram and scanvi require reference_data_id to be preprocessed first, and by explaining marker_score versus threshold behavior. It still does not explicitly state when to choose this tool over sibling annotation or domain-identification tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=false and destructiveHint=true, so the safety profile is declared. The description adds context by specifying DESeq2 and pseudobulk aggregation, and the schema mentions 'Requires 2+ samples per condition.' However, it does not explain what destructive side effects may occur or what state changes are involved, leaving a transparency gap despite annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loaded with the core purpose, followed by a concise Args block. The 'etc.' and redundant parameter list slightly reduce precision, but there is no filler or unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of the tool, the rich input schema and output schema carry most of the burden. The nested schema includes thresholds, defaults, and usage differentiation. The top-level description is minimal but sufficient for basic selection; a bit more context about prerequisites or side effects would make it more complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description lists required parameter names (condition_key, condition1, condition2, sample_key) but adds no semantics beyond the names. The input schema provides rich descriptions for every parameter, so the description adds minimal value beyond what the schema already covers.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Compare experimental conditions using pseudobulk differential expression (DESeq2).' This provides a specific verb, resource, and method. It does not explicitly name sibling tools, but the scope ('conditions' vs 'cell types') distinguishes it from tools like find_markers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The top-level description lacks usage guidance, but the input schema's nested ConditionComparisonParameters description explicitly contrasts compare_conditions with find_markers ('compares conditions ACROSS samples' vs 'cell types/clusters WITHIN a dataset'). This is useful but limited to one alternative and does not provide exclusions or other sibling comparisons.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, so there is no contradiction. However, the description adds no behavioral context beyond the annotation—it does not mention overwriting existing results, storing outputs in the dataset, or dependencies like UMAP requiring neighbors.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with the core operations front-loaded. No filler or redundant content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complex nested params object and destructive behavior, the description is only a brief headline. It omits parameter dependencies, side effects, and usage context, leaving the agent under-informed for such a configurable tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Top-level schema coverage is 0%, and the description only provides one-line glosses for data_id and params. The rich descriptions live inside the nested EmbeddingParameters schema, which the description does not surface or summarize effectively.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Compute dimensionality reduction (PCA, UMAP), clustering, and neighbor graphs,' which uses a specific verb and names concrete resources. It clearly distinguishes this from sibling tools focused on trajectory or spatial analysis.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus siblings like analyze_trajectory_data or preprocess_data. The description lists operations but does not mention prerequisites, typical use cases, or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true and readOnlyHint=false, so the agent knows this mutates state. The description adds nothing beyond that: no mention of runtime cost, GPU requirements (despite use_gpu param), reference data prerequisites, or that destructive behavior may involve writing/overwriting results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded purpose sentence followed by a compact Args block. Efficient, though the Args block restates schema field names with little added value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, open-world tool with a large nested parameter object, the description omits prerequisites (must load a reference dataset first?), method selection guidance, and any behavioral caveats. The output schema existing removes the need to explain returns, but core missing context remains.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is effectively 0% at the top level; the description only names three nested fields (method, cell_type_key, reference_data_id) without explaining method tradeoffs, required reference loading, or which methods support what. It points the agent to DeconvolutionParameters without surfacing any of its ~60 options.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: 'Deconvolve spatial spots to estimate cell type proportions.' Clear and distinguishable from siblings like annotate_cell_types or identify_spatial_domains, though it doesn't explicitly contrast with them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no prerequisites stated, no mention of choosing among the eight deconvolution methods beyond pointing out that method lives in params. No alternative tool is named.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint=false, destructiveHint=true, and idempotentHint=true, so the agent knows it's a non-read-only, possibly destructive, idempotent operation. The description adds value by specifying the default export path and the return value (absolute path). However, it does not elaborate on what 'destructive' means (e.g., overwriting existing files), which would enhance transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured: a one-sentence summary, followed by an Args list and Returns line. Every line is informative, with no filler words or redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple export tool with two parameters, the description covers the purpose, parameters, default path, and return format. The output schema is present, so return value details are not fully required in the description. It is complete enough for an agent to use the tool, though it could mention overwrite behavior given the destructive hint.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has no descriptions beyond titles, so the description carries the full burden of explaining parameters. The Args section explains both 'data_id' as the dataset ID and 'path' as the custom path with a default, which adds meaningful semantic context beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with 'Export dataset to disk for external script access', which uses a specific verb (export) and resource (dataset), and clearly states the purpose. It naturally distinguishes itself from sibling tools that analyze, visualize, or preprocess data, as this is the only export tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly states the use case: 'for external script access', which implies when to use it. It does not explicitly mention when not to use it or provide alternatives, but given the distinct purpose among siblings, the context is clear enough.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare destructiveHint=true and readOnlyHint=false, implying this operation can modify data, but the description says only 'Find' and gives no warning about what is written or overwritten. It does not add behavioral context beyond the annotations and leaves the side-effect profile undisclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loads the purpose, but the Args block is an incomplete duplicate of schema information and ends with a vague 'etc.' rather than useful detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a differential expression tool with a destructive annotation, many optional parameters, and an output schema, the description is missing critical context: what happens to the dataset, how groups are handled, and how to choose methods or parameters. It is not complete enough to support correct invocation beyond the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description names data_id, group_key, method, group1/group2, and n_top_genes, but then falls back to 'etc.' and omits sample_key, min_cells, pseudocount, and exclusion parameters. With schema_description_coverage reported as 0%, the description does not compensate by explaining parameter meanings or interactions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence states a specific verb and resource: find differentially expressed genes between groups. It is clear what the tool does, but it does not distinguish itself from nearby siblings such as compare_conditions or find_spatial_genes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool versus alternatives, nor any prerequisites or exclusions. The Args section only restates required inputs rather than explaining the selection context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate destructiveHint: true and idempotentHint: true, but the description adds no behavioral detail such as side effects (e.g., modifying the dataset, storing results), runtime implications, or auth requirements. It merely states the action without any disclosure beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with no wasted words, and the Args section provides a clear structure. However, it is almost too terse, borderline under-specified. It earns a high score for lack of fluff but loses a point for being overly minimalist.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema, the description is incomplete for a tool with 18 parameters and destructive behavior. It does not mention expected outputs, potential runtime (e.g., SpatialDE slow), or side effects. Given the complexity, the description is far from sufficient for an agent to fully understand when and how to use it effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% because the description only mentions 'params' generically with examples like 'method, n_top_genes, etc.' It does not clarify parameter formats, defaults, or relationships. The schema itself has rich descriptions, but the description fails to add high-level guidance or summary beyond listing a couple of examples.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Identify' and the resource 'spatially variable genes', which is specific and distinguishable from siblings like find_markers and analyze_spatial_statistics. It concisely captures the tool's primary function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. It does not mention conditions like needing spatial transcriptomics data, nor does it differentiate from related analysis tools. The description lacks any contextual hints for selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, but the description adds nothing behavioral: it does not say the tool writes domain labels back into the dataset, does not warn that some methods train neural networks (long runtime, GPU), and does not mention seed/reproducibility semantics. No contradiction, but negligible added value.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the purpose sentence, then a compact Args block with no filler. Well-sized, though the Args block is arguably redundant with the rich nested schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a highly complex tool (30+ nested parameters, multiple methods, GPU training) the description is thin, but the nested schema is exhaustively documented and an output schema exists, so the biggest gaps are usage context and behavioral disclosure rather than parameter knowledge.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Top-level schema description coverage is 0%, but the nested SpatialDomainParameters def documents every field in detail. The description names the key knobs (method, n_domains, resolution), giving a useful entry point, though it does not explain that method selection changes which of those knobs matter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: 'Identify spatial domains and tissue architecture.' This clearly distinguishes it from sibling analysis tools like find_spatial_genes or analyze_spatial_statistics. It stops short of naming any sibling explicitly, so no differentiation credit beyond the resource name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no mention of prerequisites (e.g. data must be loaded/preprocessed, histology requirements for spagcn), and no comparison to alternative spatial tools. The Args block only restates the two top-level parameters.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds real behavioural detail for the batch_correction=False path (shared genes retained, counts into layers['counts'], X = log1p scaled to 10k, obs and coordinates preserved, batch_key holds source dataset ID). But the default integration path is behaviourally opaque, and the destructive side effects flagged by the annotations are never explained.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in a single sentence and the Args block is terse. The final paragraph, however, restates the batch_correction=False schema description almost verbatim, so a large fraction of the description duplicates a structured field instead of adding new information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the uncorrected pooling mode is covered thoroughly. What remains missing is the behaviour of the primary integration path, whether preprocessing is required before the default call, and what the destructive hint actually implies for existing datasets.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite only 50% schema coverage, the description names the key knobs (method, batch_key, n_pcs) and explains the most consequential one, batch_correction, in operational terms rather than just its name. The nested IntegrationParameters object is largely self-documenting in the schema, so the description's contribution is proportionate rather than exhaustive.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence gives a specific verb plus resource ('Integrate multiple spatial transcriptomics samples into a unified dataset'), which is unambiguous and matches nothing else in the sibling list. It does not explicitly differentiate itself from near-neighbours such as register_spatial_data or preprocess_data, which is the only thing keeping it from a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description supplies one concrete usage scenario ('pool sections for analyze_cell_communication') for the batch_correction=False path, which is genuinely helpful routing. However, it gives no guidance on when to use the default corrected path, no prerequisites, and no statement of when this tool should be chosen over registering or preprocessing data instead.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is clear. The description adds that loading returns a SpatialDataset with cell/gene counts and metadata profiles, but does not disclose additional side effects or external access behavior beyond what annotations imply.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with Args and Returns sections, providing all necessary information in a compact and easily scannable format. No redundant or filler content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema and annotations, the description covers the essential aspects: loading data, supported data types, and return type. It doesn't address edge cases like error handling or file format details, but it is sufficient for a data loading tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description's Args block explains all three parameters, including allowed values for data_type, which compensates for the schema's empty parameter descriptions (0% coverage). This adds meaningful context beyond the raw schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Load') and names the resource ('spatial transcriptomics data'), making it clear what the tool does. It is distinct from sibling tools like reload_data and preprocess_data, and the Args section further specifies data types and behaviors.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this is the entry point for loading spatial data but does not explicitly state when to use it over reload_data or other alternatives. The data_type enum provides some context, but there is no when-to-use/when-not-to-use guidance or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate destructiveHint=true, but the description does not elaborate on what is destroyed or modified (e.g., whether it overwrites existing data, irreversibility, or side effects). The only behavioral note is a negative scope (not computing embeddings), which is more purpose-related than a behavioral disclosure. With a destructive hint, the description should warn about data overwrite or similar consequences.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured: it opens with the primary purpose, then clarifies scope limits, and ends with a compact Args section. Every sentence adds value without redundancy, making it easy for an agent to quickly grasp the tool's core function.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (many parameters, destructive behavior) and the lack of output schema details, the description is somewhat minimal. It covers purpose and the boundary with compute_embeddings, but it omits prerequisites (e.g., data must already be loaded), side effects of the destructive operation, and what the function returns. This is adequate but with clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema itself provides detailed descriptions for each parameter, so the baseline is 3. The description adds only minimal value by saying 'all have sensible defaults,' which helps convey that params can be omitted, but it does not explain any parameter semantics beyond that. The schema carries the heavy lifting for parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function with a specific verb and resource: 'Run QC, filtering, normalization, and highly variable gene selection.' It also explicitly differentiates itself from a sibling tool by stating it does not compute PCA, UMAP, clustering, or neighbor graphs, and directs users to compute_embeddings() when those artifacts are needed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context by stating that compute_embeddings() should be run afterward when downstream tools require those artifacts. This implies the tool's role in the analysis pipeline, but it does not explicitly mention when not to use this tool or list alternative preprocessors, so there is room for improvement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate destructiveHint=true, but the description does not disclose what side effects occur, such as modifying datasets, overwriting existing spatial keys, or requiring GPU resources. The return value mentions a 'registered spatial key' but does not explain whether it alters the input data. Since destructive behavior is likely, the description should clarify the nature of these changes, but it remains silent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and uses a clear structured format with Args and Returns sections. It avoids unnecessary verbiage and conveys the core purpose in two lines. It could be slightly more informative, but the structure is efficient and scannable, earning a high score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (nested parameters, two algorithms with distinct behaviors) and destructive hint, the description is incomplete. It does not mention prerequisites like loaded data, differences between method options ('paste' vs 'stalign'), or potential side effects. While an output schema exists, the description still needs to provide usage context and behavioral expectations, which it largely omits.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, but it provides only minimal information: source_id, target_id, and a vague 'params: Registration parameters (method, alignment settings, etc.)'. Source and target IDs are self-explanatory, but the nested params object contains many fields (method, stalign_a, paste_alpha, etc.) with detailed schema descriptions that are not reflected in the tool description. The agent gets insufficient guidance on parameter selection or meaning beyond the raw schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Register/align spatial transcriptomics data across sections.' This specifies a verb (register/align), resource (spatial transcriptomics data), and scope (across sections), which helps distinguish it from generic analysis tools. However, it does not explicitly differentiate from sibling tools like integrate_samples, so it falls slightly short of a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no explicit guidance on when to use this tool versus alternatives. It only describes the action and parameters, with no mention of prerequisites, exclusions, or when registration is appropriate. Usage must be inferred entirely from the tool name and general context, leaving the agent without clear direction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructive and idempotent hints; description adds prerequisite (must exist in MCP memory) and default path behavior. No contradiction; adds useful context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Compact with Args/Returns sections; every sentence provides necessary detail, no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers purpose, parameters, return, and prerequisite. With output schema and annotations present, description is sufficient, though it could explicitly state the destructive overwrite behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has no descriptions (0% coverage); description explains both data_id (must exist in memory) and path (custom path with default), fully compensating.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Reload dataset from disk after external script modifications' - a specific verb, resource, and context. Distinguishes from load_data by emphasizing reloading after modifications.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies usage after external script modifications, which is a clear context, but doesn't explicitly name alternatives or exclusions. Provides enough to know when to apply.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations flag destructiveHint=true and readOnlyHint=false, so this tool may have side effects, but the description only mentions visualization and parameters. It does not disclose overwriting behavior, file side effects, or any other consequences. This is not a direct contradiction, but the description misses important behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loaded with the purpose, followed by a pointer to the schema. The Args block is mostly redundant with the schema but remains concise and does not significantly bloat the description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the very large VisualizationParameters schema, the pointer to that schema is helpful, and the output schema covers return values. However, the description lacks workflow context, side-effect awareness, and guidance on how visualization relates to upstream analysis steps. It is minimally viable but has clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema itself is highly detailed with property descriptions, so the description does not need to duplicate that information. It usefully highlights plot_type and subtype as primary controls and points to the VisualizationParameters schema. However, the example 'genes' does not exactly match the schema property 'feature', adding slight ambiguity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description begins with a specific verb and resource: 'Visualize spatial transcriptomics data.' This clearly distinguishes it from sibling tools like load_data, preprocess_data, and find_markers. The added instruction to set plot_type and subtype further scopes the tool's functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description tells users to set plot_type and subtype and reference the schema, but it does not explain when to use this tool versus alternatives, prerequisites, or when not to use it. No exclusions or alternative tool references are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.