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

Annotations already cover the read-only/idempotent safety profile, and the description adds substantial non-obvious behavior: project-level dedup, canonical-row resolution independent of the query, why titles may not contain query terms, cross-page duplicates, and offset stepping. This is exactly the kind of context annotations cannot express.

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 use case, then return shape, then semantics, then bounds, so an agent can stop reading early. It is dense but slightly redundant: 'ids are unique within a response' and the canonical-row explanation are each restated, adding length without 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?

For a 3-parameter tool with a deceptively complex result model and pagination, nothing an agent needs is missing; the only gap is return-format detail, which the output schema already supplies.

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 full burden and does: query is required, 2-64 chars, matched over titles, blank yields nothing; limit 1-50 default 20; offset 0-10000 with exact row-skipping semantics. That is more than the schema's bare types and defaults provide.

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 ('citation-shaped NIH grant hits') and defines the record shape (id = project_num, url = OpenNIH page). It explicitly distinguishes itself as the 'citation-record wrapper' with no filters, which separates it from the filterable search_grants sibling.

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 triggering condition ('when a research or connector client needs citation-shaped NIH grant hits for a natural-language query') and exclusions ('takes no filters... returns no funding totals or provenance'). It never names search_grants as the alternative for filtered/aggregate needs, so routing is implied rather than explicit.

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