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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds meaningful domain-specific behavioral context beyond annotations: the AlphaFold confidence caveat (<70 pLDDT regions may yield incorrect pocket predictions) and the automatic PDB→UniProt resolution. This is valuable but doesn't cover rate limits or output caveats in depth.

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 with the core purpose, then retrieval scope, the first-call directive, the AlphaFold caveat, and the input rule. It is somewhat longer than strictly necessary (the AlphaFold IMPORTANT paragraph is a sizeable aside) but every block carries useful information and 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?

For a read-only characterization tool with an output schema present, the description covers purpose, retrieval contents, call ordering, and the input contract. The AlphaFold caveat pre-empts downstream misuse, and return values needn't be explained since an output schema exists.

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 — and it does: it gives concrete example values ('1M17', 'P00533') and states the resolution behavior when a PDB ID is provided. Both parameters are addressed, though it doesn't clarify precedence if both are supplied or that both are optional.

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+resource: 'Establish biological context for a drug target protein', then enumerates exactly what is retrieved (function, family, subcellular location, disease associations, AlphaFold confidence). This makes the tool's scope unambiguous and clearly distinguishable from siblings like GetBindingSites or SearchTargetLiterature.

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?

Explicitly instructs 'This should be your FIRST call — all downstream analysis depends on this context', giving a clear ordering prerequisite relative to the sibling analysis tools. The either/or input rule ('Provide EITHER a PDB ID OR a UniProt accession') further guides correct invocation.

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 cover read-only/idempotent safety, and the description adds genuine behavioral detail: non-conserved positions are flagged per species individually, default species and ordering behavior, and interpretation thresholds. It does not address failure modes such as missing ortholog sequence or invalid residue positions.

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 with the core action and its translatability rationale, then thresholds, then parameter guidance. Mostly every sentence earns its place, though the macaque superiority aside is slightly digressive.

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 formatting is not required, and the description adequately covers inputs, defaults, and how to read results. Remaining gaps are edge cases (invalid positions, species without orthologs) rather than core 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?

Schema coverage is 0%, so the description carries the burden, and it does: uniprot_id is identified as the human accession, residue_positions must come from GetBindingSites, and the species parameter's value domain ('mouse', 'rat', 'cynomolgus'), default, and restrict/reorder behavior are supplied even though the schema has no enum. Residue numbering convention (UniProt vs. structure numbering) is left ambiguous.

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 ('check conservation at binding site residues') with an explicit scope (mouse, rat, cynomolgus). It is clearly separable from siblings such as CheckKnownVariants or CharacterizeTarget, and it names GetBindingSites as the upstream source of its inputs.

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?

Gives a clear context and motivation (preclinical translatability) plus a prerequisite chain ('residue positions from GetBindingSites'). It also prescribes what to do at each conservation band. It stops short of naming alternatives to use when conservation is poor or when a different check is wanted.

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 readOnly/idempotent/non-destructive/openWorld, so safety is covered. The description adds real behavioral context beyond that: the underlying data source (UniProt Natural variant + Mutagenesis features) and how to interpret a positive hit as a drug-resistance risk signal. Output format is deferred to the output schema.

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 action, follows with the interpretation rationale, and ends with the concrete input instruction. Well-sized with no filler, though the middle explanatory sentence is somewhat long.

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 two-parameter read-only lookup with an output schema present, the description covers purpose, data provenance, and input sourcing sufficiently; an agent has what it needs to call it correctly. Minor gaps remain around position format.

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 carries the burden. It does add value by specifying the accession must be human and that residue_positions come from GetBindingSites, but it gives no format details such as numbering convention or expected position range, leaving meaningful ambiguity for a 2-parameter tool.

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: 'Flag known sequence variants and mutagenesis hits at binding-site residues.' It also names the upstream sibling (GetBindingSites) as the source of positions, which helps separate it from CharacterizeTarget/CheckConservation, though it never explicitly contrasts with those siblings.

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?

Gives clear context: call it with a human UniProt accession plus positions obtained from GetBindingSites, and explains why (documented variants mark pockets that mutate under drug pressure, a risk signal for design choices). No explicit when-not-to-use or exclusion of alternatives, so it stops short of a 5.

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 readOnly/idempotent/non-destructive/open-world, so safety is covered. The description adds genuinely new behavioral context beyond that: it is 'the heaviest tool — downloads several coordinate files,' implying cost/latency, and it clusters pockets by residue overlap rather than returning raw sites. It omits pagination/result-size behavior, but the cost signal is a real value-add.

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 what the tool does, then mechanics, then input guidance, in three tight sentences with no filler. Every sentence carries information the agent needs.

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-value explanation is not required, and the description covers purpose, cost, and ID selection adequately for a fan-out aggregation tool. The remaining gap is the undocumented `limit` parameter and the absence of any explicit alternative-selection rule against GetBindingSites.

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 explains uniprot_id vs pdb_id and marks uniprot_id as preferred, which is useful, but it never explains the third parameter `limit` (apparently the number of top structures) nor the mutual exclusivity of the two ID options. Two of three parameters get meaning; one is left fully undocumented.

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 ('Map the union of binding pockets across all structures of a target') and explicitly names the sibling it builds on ('Fans out GetBindingSites'), so an agent can distinguish aggregation from the single-structure lookup. The clustering-consensus concept (recurrent vs one-off pockets) sharpens the purpose further.

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?

Gives concrete input selection guidance ('Provide uniprot_id (preferred) or pdb_id') and implicitly frames the tool as the multi-structure consensus counterpart to GetBindingSites. However, it never states the exclusion condition explicitly (e.g. use GetBindingSites instead when you only need a single structure), so the when-not is left to inference.

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 cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds substantial behavior beyond that: it filters crystallization artifacts (glycerol, PEG, sulfate), classifies sites by type, and reports per-site druggability and modality recommendations with concrete thresholds. This is exactly the kind of non-obvious processing behavior an agent needs.

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 map statement is front-loaded, followed by method, output contents, and usage in a logical order with efficient bullet lists. It is somewhat long relative to a one-parameter tool, but nearly every sentence adds decision-relevant 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?

Given an output schema exists, the description need not enumerate return values, yet it usefully previews site classification and druggability outputs. Combined with the guidance on which IDs to pass and the multi-structure strategy, an agent has everything required to invoke it correctly.

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 single parameter (pdb_id) has 0% schema description coverage, so the description must carry the load. It does so partially by establishing that the argument is a specific PDB ID obtained from GetRelatedStructures, which clarifies the expected value provenance, though it gives no format example or validity constraints.

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 ('Map all known binding sites in a protein structure') and even specifies the method (analyzing non-polymer entities from co-crystallized ligands). It is clearly distinct from data-fetching siblings like GetRelatedStructures, though it never explicitly contrasts itself with ConsolidateBindingSites, so it stops short of full sibling differentiation.

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 clear context: call this on specific PDB IDs surfaced by GetRelatedStructures, and for comprehensive coverage call it across multiple structures with different ligands. That names the upstream tool and the multi-call strategy, but there is no explicit 'do not use this when...' exclusion versus ConsolidateBindingSites.

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 establish read-only, idempotent, open-world, non-destructive behavior, so the safety profile is covered. The description adds useful context about what the data reveals (SAR availability, clinical reach, landscape crowding), but discloses no auth needs, rate limits, or data-freshness caveats.

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 with the core purpose, then progressively adds interpretation guidance and the parameter constraint. Well-sized and structured, though the middle interpretive paragraph is advisory rather than strictly operational and could be trimmed.

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-value details are appropriately omitted, and the mutual-exclusion constraint on the two optional parameters is stated. For a two-parameter read tool this is close to complete; the only gap is that neither parameter is required despite the either/or instruction, which the agent must infer.

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 0%, so the description must carry the parameter burden, and it does the most important part: the two IDs are mutually exclusive alternatives ("Provide EITHER") with a stated preference (UniProt for accuracy). Neither the anyOf/null schema nor the 0% coverage conveys the either-or constraint or the accuracy tradeoff.

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 (Retrieve) and resource (bioactivity landscape for a drug target from ChEMBL) and enumerates what the result covers: compounds tested, potency, clinical progression, competitive density. It carves out a distinct domain relative to siblings like GetBindingSites and SearchTargetLiterature, though it never names those siblings to sharpen the boundary.

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?

Explicitly frames the decision this tool supports (known vs novel binding sites, crowded vs untargeted landscape), which tells the agent when the tool is worth calling. It does not name an alternative tool or state when NOT to use it, so it falls short of full routing guidance.

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 cover readOnly, idempotent, openWorld and non-destructive, so the safety bar is met. The description adds useful behavioral context beyond that: results are sorted by resolution, and the interpretation guidance (many co-crystal structures = rich landscape; apo-only = less evidence) tells the agent what the output means. It stops short of describing pagination or the role of the limit parameter.

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 with the core action, then rationale, then workflow placement. The middle paragraph on structural coverage interpretation is slightly expansive but delivers genuine decision value rather than 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, so return values need no explanation, and the description covers purpose, workflow position, and result interpretation. The one real gap is parameter documentation, which is scored separately, so the description is otherwise complete for this 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% and the description never addresses any of the three parameters. It implies target-based lookup (consistent with uniprot_id), but the limit default, the pdb_id option, and how the two identifiers interact are left entirely undocumented in both schema and 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?

States a specific verb and resource: 'Find all PDB structures for a target protein', with the ordering by resolution and the scope (all available experimental structures). This is clearly distinguishable from siblings like GetBindingSites and CharacterizeTarget, which the description names directly.

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?

Gives explicit sequencing: 'Call this AFTER CharacterizeTarget and BEFORE GetBindingSites'. It also explains the purpose of that placement (to identify which structures to analyze for pockets), so an agent knows exactly when to invoke it in the pipeline.

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 cover the safety profile (readOnly, idempotent, non-destructive, openWorld). The description adds the behavioral trait that matters most here: this is an external literature source used as a final cross-check after internal databases, which cannot be inferred from annotations. It omits any note on result freshness or rate limits, keeping it short of a 5.

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 in the first sentence, then uses compact bullets for context values and a clearly signposted ordering instruction. Slightly verbose in repeating 'most relevant to planning a new binder design effort', but every block is scannable and useful.

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-format explanation is unnecessary; the description closes the remaining gap by defining scope, context options, and call ordering. Only the undocumented `max_results` behavior leaves a minor hole.

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 carries the burden and does partly compensate by enumerating four meaningful `context` values (allosteric, resistance, antibody, oncology). However, `gene_name` and `max_results` receive no explanation at all, so the compensation is incomplete.

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 (Search) and resource (PubMed literature) plus the topical scope: binding site characterization, allosteric mechanisms, resistance mutations, prior design campaigns. No sibling tool covers literature, so the differentiation is implicit but unmistakable against the database-oriented siblings.

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?

Explicitly instructs 'Call this LAST — after CharacterizeTarget, GetRelatedStructures, GetBindingSites, GetLigandHistory, and CheckConservation' and explains why (to catch insights not captured in database records, e.g. cryptic sites from MD). That is both when-to-use and sequencing guidance against named alternatives.

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