chembl-mcp-server

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, covering the safety profile. The description adds value by specifying the return contents (row count, kind, column names/types) and the environment requirement, which the annotations do not convey.

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 three short, tightly packed sentences. The primary purpose is front-loaded, and every sentence adds necessary information (what it lists, why to use it, return format, and a prerequisite). No filler or redundant phrases.

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 tool with one parameter, an output schema, and annotations covering mutability, the description covers everything needed for correct invocation: its role relative to a sibling, the return content, and an environment requirement. Nothing essential is missing.

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 covers the single parameter (canvas_id) with a description ('Canvas ID returned by chembl_get_bioactivities (spilled: true)'). The tool description does not add any new meaning beyond the schema, so a baseline score of 3 is appropriate.

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 (List), a concrete resource (tables and columns staged on a canvas), and the source tool (chembl_get_bioactivities). It also names the sibling chembl_dataframe_query to distinguish this inspection tool from the query tool, making its purpose unmistakable.

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 explicit usage context: 'inspect before calling chembl_dataframe_query to write correct SQL' and states an environmental prerequisite (CANVAS_PROVIDER_TYPE=duckdb). This tells the agent precisely when to use the tool and what it enables.

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=true and idempotentHint=true, and the description reinforces this by calling it a 'read-only SQL SELECT'. Beyond that, it transparently discloses the two output bounds (truncated and rendered_rows), explains how they relate to row caps and character budgets, and states the dependency on CANVAS_PROVIDER_TYPE=duckdb. No contradiction with 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 long but information-dense, with each sentence serving a purpose. It is front-loaded with the core purpose, then details table naming, example SQL, bounds, and paging. While not terse, it is well-structured and avoids redundancy, making it efficient for an agent to parse.

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 (SQL query over staged tables with bounds and paging), the description covers all essential aspects: purpose, table naming conventions, an example query, behavior when limits are hit, how to page, and the runtime requirement. The presence of an output schema is handled by the description explaining the bound fields, so nothing critical is missing.

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 100%, so the baseline is 3. The tool description adds value by giving an example SQL statement and clarifying that tables are referenced by names returned by chembl_get_bioactivities, which reinforces the schema. However, the parameter descriptions in the schema already convey most of the necessary meaning, so the incremental contribution is moderate.

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 a specific verb and resource ('Run a read-only SQL SELECT over the bioactivity rows...'), and immediately distinguishes itself from the sibling tool by stating 'across the FULL set, not the inline preview'. It also names the staged tables and views, making the tool's role 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 explicitly tells the agent when to use this tool versus the preview provided by chembl_get_bioactivities, and points to chembl_dataframe_describe for discovering staged tables. It also gives concrete paging instructions ('append e.g. LIMIT 500 OFFSET 500 and re-call') and clarifies that aggregate computations should be done here.

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 declare readOnlyHint, openWorldHint, and idempotentHint, which cover safety and idempotency. The description adds behavioral context beyond annotations by explaining the significance of the confidence score (9 = direct assay, lower = homologous/indirect) and how the result maps to data provenance. This helps the agent interpret the output correctly without contradicting 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 a single, well-organized sentence that front-loads the core purpose, then provides necessary details. It avoids fluff and each clause adds value. It could arguably be split into two sentences for readability, but it remains concise and structured.

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 has only one parameter, an output schema (which likely lists the returned fields), and the description covers the key semantic details (confidence interpretation, comparability use case), the definition is fully adequate. An agent can correctly invoke and interpret the tool without ambiguity.

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 already documents the parameter with an example, but the description reinforces the source of the ID ('from a chembl_get_bioactivities row'), adding practical guidance on how to obtain the value. With 100% schema coverage, this additional contextualization elevates the score above the baseline.

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: it provides assay provenance (description, type, target, organism, confidence score) for a bioactivity row. It uses a specific verb ('get') on a specific resource ('assay'), and distinguishes itself from siblings by referencing the source (bioactivity row) and the purpose (judging comparability).

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 explicitly instructs to supply assay_chembl_id from a chembl_get_bioactivities row and gives a concrete use case ('to judge whether two measurements are comparable before ranking them together'). While it does not explicitly state when not to use it, the guidance is clear and sufficient for an agent to decide. It does not name alternative tools, but the context implies this is the sole route for assay provenance.

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 readOnlyHint, openWorldHint, and idempotentHint, but the description adds substantial behavioral context: the potency_view split with exact semantics of each side, the truncation cap with 'truncated' flag, the behavior of totalCount across views, and the canvas staging behavior (overwrite vs. coexist). It even explains why rows are not merged. This is precisely the kind of context that lets an agent predict side effects and data shape without risking a wrong call.

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 long but every sentence carries information. It front-loads the core purpose, then systematically covers invocation, filtering, the two-view split, spill behavior, and tool integrations. There is no filler or repetition; each clause earns its place. The structured flow from 'what' to 'how' to 'edge cases' makes it easy for an agent to parse quickly.

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 (9 params, two views, spill logic, coordination with four sibling tools), the description is remarkably complete. It covers error conditions, partition semantics, truncation, canvas behavior, and cross-tool handoffs. The presence of an output schema covers return-value details, so the description appropriately focuses on invocation and behavioral nuances, leaving nothing ambiguous for a competent agent.

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?

Though schema coverage is 100%, the description vastly enriches parameter meaning. It explains pchembl_value_min semantics, the scientific rationale for setting standard_type ('compare like with like'), the exact partition defined by potency_view, and the behavior of canvas_id across views. It goes beyond the schema's field descriptions to teach the agent how the parameters interact (e.g., pchembl_value_min only valid on potency_ranked). This is high-value added semantics.

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 a crisp purpose statement: 'flagship compound↔target bioactivity bridge' and immediately enumerates the three invocation modes (molecule-only, target-only, molecule+target) with their scientific use cases (deconvolution, lead finding, selectivity). This clearly distinguishes it from siblings like chembl_search_molecules or chembl_dataframe_query, and the verb 'get' plus resource 'bioactivities' makes the action 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 provides explicit preconditions ('Supply at least one... supplying neither is an error'), explicit conditions for narrowing (both IDs), a warning against mixing measurement types, and clear direction on when to use companion tools (chembl_dataframe_describe/query for large result sets, and the condition for spilling needing duckdb). This goes far beyond generic guidance and gives an agent actionable decision rules.

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, openWorldHint, and idempotentHint, but the description goes far beyond them by explaining the retrieval-state semantics: an empty mechanisms/indications array is meaningful only when the corresponding status is 'complete', while 'failed' and 'truncated' have distinct interpretations. This prevents the agent from misreading empty arrays as definitive absence of data—a critical behavioral nuance not captured by annotations. It also notes the chaining to bioactivities, adding functional 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 dense yet efficient: it front-loads the core output, then covers input source, distinction from an alternative server, chaining to a sibling tool, and finally the crucial status semantics. Every sentence carries essential information—no filler. The structure is logical and well-organized, making it easy for an agent to parse despite its length.

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, the presence of an output schema, and the annotations, the description covers all critical aspects an agent needs: what data is returned, where the input comes from, how it differs from an alternative view, how to chain to related tools, and how to correctly interpret empty results via the status fields. It addresses a likely pitfall (interpreting empty arrays) and leaves no obvious gaps for correct invocation.

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 coverage is 100% and the single parameter already has a detailed description ('ChEMBL molecule ID (from chembl_search_molecules), e.g. "CHEMBL939" for gefitinib.'). The tool description reiterates the source and adds an example, reinforcing the parameter's origin. Since the schema alone is nearly sufficient, the description adds marginal but useful value (source tool and concrete example), so a 4 is appropriate above the baseline of 3.

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 a clear verb and resource: 'Pharmacology for a drug (molecule)' followed by a specific list of what it returns (mechanisms, targets, action type, first-approval year, indications with max phase). It explicitly names the input ('Supply molecule_chembl_id') and distinguishes itself from the openfda server's label/adverse-event view, making it easy to differentiate from siblings like chembl_get_bioactivities or chembl_get_assay.

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 strong contextual guidance: it states the input comes from chembl_search_molecules and differentiates this tool from the openfda server's view, indicating an alternative. It also chains to chembl_get_bioactivities via target_chembl_id, suggesting when to use that related tool. However, it does not explicitly state 'when not to use' this tool beyond the openfda distinction, and it lacks a crisp 'use this when you need curated pharmacology' statement, leaving some inference to the agent.

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 (readOnlyHint=true, idempotentHint=true, openWorldHint=true) already carry the safety profile, so the description rightly focuses on behavior beyond that: the returned column set on every row, the Tanimoto-only-for-similarity caveat, pagination via nextCursor/cursor, and the cross-tool chaining. No contradiction with annotations — 'search', 'find', and 'read the next page' all align with readOnly. Could earn a 5 with explicit remarks on locking/limitations, but the pagination and return-format disclosure already exceed annotation coverage.

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?

Six dense sentences, logically ordered: purpose → modes → requirements → return fields → chaining → pagination. The 'Discovery entry point' framing is front-loaded. It is longer than average, but the tool has 7 parameters and 4 search modes, so the length is earned. Only minor tightening is possible (e.g., max_phase_min is absent from the description but well covered by the schema), so not a 5.

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?

Comprehensive for a complex tool: all search modes, input requirements, return columns, chaining targets, and pagination are covered. An output schema exists, so return-value explanation is a bonus rather than a need. Minor gaps — max_phase_min usage in the description and explicit filtering semantics — are fully handled by the parameter schema and output schema, so nothing an agent needs to call it correctly is missing.

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 100%, so the baseline is 3 and the schema already documents every parameter well (ranges for similarity_threshold, cursor semantics, enum meanings for search_type). The description adds genuine cross-parameter combination logic — which fields are required in which mode, and that only limit may change when re-sending a cursor — which is valuable. But it does not add per-parameter meaning beyond the schema, keeping this at a solid 3.

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 ('Discovery entry point for compounds') plus the two distinct call shapes — name/ID/InChIKey lookup vs. structure search (exact | similarity | substructure). It differentiates from siblings by scope: chembl_search_targets searches targets, and the chain tools chembl_get_bioactivities / chembl_get_drug_info are downstream consumers, while this is the molecule search entry point. A tool like get_assay is clearly distinct. Nothing is ambiguous about what this tool does.

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?

Provides clear conditional context: default search_type=name needs query, structure modes need structure, and 'At least one of query or structure is required.' It also gives an actionable routing instruction — 'Chain molecule_chembl_id into chembl_get_bioactivities or chembl_get_drug_info.' It lacks explicit when-not-to-use or named exclusions against siblings, but the chaining direction and search-selector guidance make usage clear.

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=true, openWorldHint=true, and idempotentHint=true, covering safety and non-destructiveness. The description adds value by detailing the return payload (each target's type, organism, component UniProt accessions, and gene symbols) and the pagination behavior (nextCursor, pass back with same filters). This goes beyond annotations without contradicting them.

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—three sentences—yet delivers the purpose, required inputs, optional filters, return structure, and pagination guidance. It is front-loaded with the core purpose and workflow link, and every sentence contributes. No fluff or repetition of schema details.

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 7-parameter search/resolution tool with no required parameters, the description is complete. It covers input options, precision ranking, filtering, return fields, and pagination. The existing output schema absorbs the need to describe return values in detail, and annotations already indicate safe read-only idempotent behavior. Nothing an agent needs to invoke it correctly is missing.

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 100%, so each parameter is already documented. The description adds meaningful nuance beyond the schema: it flags accession as the most precise resolver (from the uniprot/protein server), clarifies that gene_symbol and organism are case-insensitive exact matches, and explains the cursor semantics in detail (only limit may change when redeeming). This enriches the schema's bare parameter definitions.

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 explicitly states the verb 'Resolve' and the resource (protein/gene/UniProt to ChEMBL target ID), and ties it to a specific downstream workflow (needed by chembl_get_bioactivities). This clearly distinguishes it from sibling search tools like chembl_search_molecules or chembl_get_drug_info, which serve different resolution needs.

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 clear guidance on when to use this tool (to resolve an identifier before the bioactivities step) and specifies that at least one of accession/gene_symbol/query is required, with a hint that UniProt accession is the most precise. It also explains pagination via cursor. However, it does not explicitly name alternatives or state when NOT to use this tool in favor of a sibling, so it's slightly shy of a 5.

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