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

Annotations already declare readOnly, openWorld, and idempotent hints, so the safety profile is covered. The description adds genuinely useful behavioral context: pagination mechanics ('page past maxResults with offset'), that results are a 'page' of AIDs, and the open-world nature of results ('Popular targets may have thousands of assays'). These insights go beyond the structured 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?

Three sentences with zero waste. The first states the primary action, the second enumerates valid inputs with concrete examples, and the third describes output plus forward-routing. Every sentence earns its place and the most important information is front-loaded.

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 4-parameter tool with a full output schema, the description covers all necessary call information: inputs, pagination, and the natural next step via pubchem_get_summary. The only slight gap is not describing end-of-pagination behavior, but this is minor given the schema handles return semantics and the description covers the full user journey.

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% with thorough descriptions on offset, maxResults, targetType, and targetQuery, including examples. The description reinforces the identifier types and pagination but adds little beyond what the schema already provides. Since the schema does the heavy lifting and the description is consistent with it, this lands at the baseline 3 for high schema coverage.

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 and resource: 'Find PubChem bioassays associated with a biological target', which clearly distinguishes this search tool from its siblings like pubchem_get_summary (retrieval) and pubchem_search_compounds (different resource). It also specifies the exact output (AIDs) and the accepted identifier types. This is fully non-tautological and specific enough to route an agent correctly without opening the schema.

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 context: use this when you have a biological target and need related assays, and it routes the agent to 'pubchem_get_summary' for further exploration. However, it doesn't explicitly state when NOT to use this tool (e.g., if you already have an AID, use get_summary directly) or contrast with pubchem_search_compounds. The sibling reference is helpful but could be more exclusionary.

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