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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description still adds genuinely non-redundant behavior: the upstream source (FPDS) and, importantly, the result-set size ('ten at a time'), which signals pagination pressure that the agent would otherwise only discover empirically. It stops short of describing ordering or what happens when no filters are supplied.

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?

A single dense sentence, front-loaded with the resource, then scope, then filters, then page size, then provenance. Every clause carries information; nothing is padded or repeated from the title.

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 5-parameter search tool with no output schema, the description covers filters and page size but leaves meaningful gaps: whether multiple filters combine with AND, whether omitting all filters returns the whole corpus, any default fiscal year, and what an award record actually contains (amount, date, agency). An agent can call it, but not predict its results well.

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 carry the burden, and it largely does: 'vendor name', 'NAICS code', 'place-of-performance state' and 'fiscal year' map onto recipient, naics, state and fiscal_year with added meaning (place of performance, not vendor location). Only 'start' is left implicit, inferable from 'ten at a time' but never named as an offset.

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 names a specific resource ('US federal contract actions (awards and modifications)') and enumerates the exact filter dimensions, so the agent knows precisely what this retrieves. It does not explicitly contrast with siblings such as company_financial_facts or entity_lookup, though the contract-award framing makes the distinction reasonably inferable.

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 rather than stated: the list of queryable dimensions (vendor, NAICS, state, fiscal year) tells the agent what contexts this tool serves, but there is no explicit when-to-use rule, no prerequisites, and no mention of alternatives or when-not to use it.

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