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

The description goes beyond the annotations by disclosing that the current preview is 'always free' and that it 'explicitly marks unresolved project relevance, document, or award-history evidence.' This adds useful behavioral context not present in readOnlyHint, openWorldHint, idempotentHint, or destructiveHint. It does not describe all side effects, but the annotations already cover the essential safety profile.

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 two sentences, front-loaded with the primary use case, and every clause earns its place: the trigger condition, the scoping constraints, the preview behavior, and the explicit exclusions. There is no redundant restating of the tool name or schema details.

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?

With an output schema present, an agent does not need the description to explain return values. The description covers invocation trigger, exclusions, and an important behavioral note about unresolved evidence marking. It stops short of explicitly distinguishing this tool from get_federal_grant_evidence_pack, which is the closest sibling, so a small completeness gap remains.

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 50%, with only opportunity_id documented in the schema. The description adds broad semantic context by calling organization a 'non-personal organization profile' and opportunity_id the 'official opportunity record,' but it does not explain nested organization fields such as can_meet_cost_share or requested_amount_usd. It partially compensates for the schema gap but does not fully cover the parameters.

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 verb and resource: a 'sourced go/no-go pursuit screen' for 'one U.S. federal grant', and clarifies the targeting via 'non-personal organization profile' and 'official opportunity record'. It also contrasts with discovery, legal eligibility, award prediction, drafting, and submission, which helps differentiate it from siblings like search_federal_grants.

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 opens with 'Use this when...' and provides clear exclusions: 'Do not use it for discovery only, legal eligibility advice, award prediction, drafting, or submission.' This gives an agent both positive and negative invocation conditions without needing to infer when the tool is appropriate.

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