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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, and the description goes beyond them with two substantive caveats: stale/dark gaps are retained rather than filled, and the content hash proves non-alteration only, not attestation or publication-time proof. These are real limits an agent would otherwise misread as guarantees.

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?

Three tight sentences, front-loaded with what the packet is and how to key it, followed by caveats. Dense domain jargon ('stale/dark gaps', 'attestation') slightly raises interpretation cost but no sentence is 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?

With no output schema, the description carries the burden of describing the return artifact, and it does so adequately: a cited packet that preserves gaps and carries a content hash with limited guarantees. What is missing is any sense of packet shape, size, or citation format.

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 coverage is 100% and the single parameter is documented as 'exact Failure Radar slug or full institution name'. The description still adds value by clarifying that matching is exact and that a full name must be unique and normalized — behavior the schema does not state.

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 — a cited human review packet — and pins the retrieval key to an exact slug or unique normalized full name. The verb is implicit (packet is a noun phrase), and it never names a sibling such as evidence_institution or failure_radar_institution, so differentiation is left to inference.

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?

'No fuzzy match or new score' tells the agent what this tool will not do, which implicitly routes fuzzy lookups and scoring elsewhere. However, no alternative sibling is named and there is no positive statement of when this packet is the right choice over evidence_institution or institution_research_coverage.

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