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

With no annotations, the description carries the full burden and does real work: it discloses that sort and the closing-window apply only to the fetched window, and that the response signals when the window is narrower than the total hit count. That truncation caveat is behavior an agent could not get from the schema. What's missing is operational context (auth, rate limits, pagination beyond 'rows').

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 resource and platform in the first clause, then the return fields, then the filtering options. It runs long in a single em-dash-chained sentence, but every clause (defaults, return contents, window caveat) carries information an 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?

For a six-parameter search with no output schema and no annotations, the description covers what the tool returns, the important default (posted), and the result-truncation semantics. Minor gaps remain around keyword matching behavior and how the narrower-window notice is surfaced, but nothing prevents a correct call.

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%, so baseline is 3, and the description earns above that by explaining the interaction between rows, sort, and closing_within_days — specifically that sort/window operate on the fetched window rather than the full result set. That is semantic meaning absent from the per-parameter schema strings.

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 with scope qualifiers: 'Search live federal grant opportunities on Grants.gov (posted by default)', plus an enumeration of what comes back (hit count, agency, dates, CFDA numbers). This is clearly distinct from a contracts or businesses search, though it never names the closest sibling, grants_search_programs, to explain the opportunity-vs-program split.

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 is implied through parameter guidance ('Filter by agency code; sort by close date; or restrict to grants closing within N days') rather than stated as when-to-use conditions. There is no exclusion telling an agent when to prefer grants_search_programs or contracts_search_opportunities, leaving the sibling choice to inference from the resource noun alone.

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