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

Annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false) are sparse and do not conflict. The description adds valuable behavioral context: it 'reads the official revision history' and reports 'what Grants.gov itself declared changed' alongside computed differences, and explicitly lists what it does not do. This goes beyond the annotations to clarify the tool's data source and limitations.

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?

Two well-structured sentences: the first clearly explains the purpose and output, the second lists explicit exclusions. It is front-loaded and contains zero redundant wording, making it easy for an agent to parse quickly.

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?

Given an output schema exists (has_output_schema=true) and only two parameters are involved, the description sufficiently covers the tool's scope and limitations. It mentions it is for U.S. federal grants and specifies what it reports, which is enough for correct invocation. A minor gap is not explaining how 'since_revision' affects behavior, but the schema covers that.

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?

The input schema fully documents both parameters (opportunity_id and since_revision) with descriptions and constraints, so schema coverage is 100%. The description does not add extra parameter-level meaning beyond what the schema already provides, so a baseline score of 3 is appropriate.

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 ('compare'), a resource ('revisions of a U.S. federal grant opportunity'), and enumerates the exact kinds of changes covered (deadlines, cost share, eligibility, funding). It also clarifies it reports before/after values and significance, which distinguishes it from siblings like analyze_federal_grant or get_grant_document_manifest.

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?

Explicitly states when to use ('when the user needs to know what changed between revisions') and provides clear exclusions ('does not read announcement documents, assess eligibility, predict an award, draft, or submit'). This effectively routes the agent away from sibling tools that handle those functions.

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