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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial domain behavior on top: ranking is by money actually obligated, and two categories (shared_award rows and ceiling/not-to-exceed awards) are excluded from the total and reported alongside, with a rationale for why. That is exactly the kind of non-obvious behavior an agent could not infer from the schema or annotations.

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 and example queries, then a supporting paragraph explaining the two held-out award types. The rationale sentence is longer than strictly necessary but every claim (combined program value vs. one company's share; lifetime maximum vs. window money) is substantive 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?

There is no output schema, so the description must convey what comes back; it does explain that rankings are by obligated money and that excluded categories are reported alongside, which is the key return-value nuance. It stops short of describing the shape of the result (fields, ordering ties, pagination), leaving a small gap for a tool with no output schema.

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 100%, so 'by', 'days', and 'limit' are already fully documented in the schema. The description only echoes the window concept ('recent window') and implies a top-N truncation without adding syntax, defaults, or edge-case semantics beyond the schema. Baseline 3 applies.

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 precise verb (ranks) plus ranked dimension (contractors or service branches) and the metric (total defense contract award value in a recent window), with concrete example phrasings that pin the intent. It is easily distinguished from siblings like dod_awards_search, dod_awards_recent, and dod_awards_coverage, which do not rank by obligated value.

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 example queries ('who are the top defense contractors this month', 'which service branch awarded the most this quarter') make the when-to-use case clear and implicitly steer away from raw search/list tools. However, it never names an alternative sibling or states an explicit exclusion, so the routing guidance is contextual rather than explicit.

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