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

Beyond the annotations (idempotentHint, readOnlyHint, destructiveHint), the description discloses meaningful behavioral details: it is a limited free-beta tool, never requests payment, has a global daily capacity, and counts only newly released complete results. It also clarifies idempotency semantics by instructing to reuse request_id for retries. No contradictions with 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?

The description is compact and front-loaded with the core purpose. Each sentence adds distinct value: usage context, beta limitations, retry behavior, and non-goals. There is no redundant or filler content.

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?

The definition is highly complete for an agent: it covers when to use, what not to do, idempotency, quota behavior, and the availability of an output schema covers return values. Minor gaps include no explicit guidance on what to do if the daily capacity is exhausted and no elaboration on what 'hard-gate' means, but these are not critical to invoking the tool correctly.

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 67%, so request_id and opportunity_id are already documented in the schema. The description reinforces request_id retry behavior but adds no new meaning for organization or its nested fields. The organization parameter lacks a description at the top level, though its nested properties are self-explanatory.

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 states a specific action ('get'), a concrete resource ('complete, versioned hard-gate and award-history evidence pack'), and a clear scope ('one U.S. federal grant'). It also differentiates from siblings by explicitly listing what it does not do, such as evaluate relevance, determine eligibility, or predict awards.

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?

It explicitly says to use this tool 'after search or preview when the user wants a complete, versioned hard-gate and award-history evidence pack.' It adds exclusions ('does not evaluate semantic project relevance, determine legal eligibility, predict an award, draft, or submit') that help an agent choose alternatives among siblings.

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