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

The annotations already declare readOnlyHint=true, so the description doesn't need to repeat that. However, it adds value by specifying exactly what the tool returns (score, authorship tier, hashes, anchor state, ledger status), going beyond the bare annotation. It doesn't mention any side effects or prerequisites, but since it's a read operation and the annotation covers that, this is sufficient. The absence of any destructive language aligns with the readOnlyHint, so no contradiction.

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, both dense with information. The first sentence lists the key data points returned, and the second gives a clear use case. There is no fluff or redundancy, making it concise and well-structured. It earns a high score for efficiency, though not a 5 because it could potentially include more specific examples or formatting hints, but it is already quite tight.

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 the tool's simplicity (one parameter, no output schema, read-only annotation), the description covers all critical aspects: what it does, what it returns, and when to use it. However, it doesn't mention potential errors (e.g., what happens if the certificate id doesn't exist) or rate limits, but these are less critical for a read-only verification tool with a straightforward purpose. The absence of an output schema means the description partially compensates by listing the returned fields, which is good, but it could be slightly more explicit about the response 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?

The schema has only one parameter, certificate_id, which is clearly named as an identifier. The schema description coverage is 0%, but with a single parameter that is self-explanatory from its name, the description doesn't need to add much. The description mentions 'by id' which matches the parameter, but it doesn't specify the format (e.g., UUID vs. string) beyond what the type string implies. Since this is a common identifier type, the baseline 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 clearly states the tool's function: to check a DEUSPROOF certificate by id, listing the specific types of information returned (score, authorship tier, hashes, Bitcoin anchor state, ledger status). It distinguishes itself from sibling tools by specifically addressing certificate verification, whereas siblings like certify_creation or claim_authorship are for creating or claiming, making this the go-to for validation.

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 description explicitly tells the agent when to use this tool: 'Use it to confirm a claim someone shows you.' It implies the context of verifying an existing certificate, which contrasts with sibling tools that create or manage certificates. It clearly directs the agent to use this when validation is needed, making it distinct from the creation-focused siblings.

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