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

Beyond the annotations (readOnlyHint, destructiveHint), the description discloses significant behavioral details: the hashing is purely local in memory, no API call is made, nothing is stored or forwarded, and no key is needed. It also clarifies that the tool returns a hash and URL, not a verdict, which is critical for the agent to understand the tool’s capability boundary.

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 (5-6 sentences) and front-loaded with the primary purpose. Every sentence adds distinct value: local execution, no storage, no verdict, sibling differentiation, usage guidance. There is no redundancy or 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?

Given the low complexity (1 parameter, no output schema, no enums) and the presence of rich annotations, the description covers all necessary aspects: what the tool does, what it returns (sha256 and URL), its limitations (no verdict), and exactly when an agent should choose this tool versus verify_attestation. The description is fully self-contained.

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?

With 100% schema description coverage, the baseline is 3, but the description adds valuable context: it explains that pdfBase64 is the file the agent 'is holding', reiterates the in-memory hashing, and describes the output (sha256 and verify URL) even though no output schema exists. This compensates for the missing structured output definition.

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 verb and resource: 'Turn PDF bytes ... into their SHA-256 digest and the matching kamy.dev/verify/{sha256} page URL.' It also distinguishes itself from the sibling verify_attestation by labeling itself as 'the first half of a check' and noting it returns no verdict.

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 provides explicit when-to-use guidance: 'Use this whenever you have the file itself; use verify_attestation directly when someone has already given you a digest.' It also explains the tool's role as the first half of a two-step process, giving the agent clear context for decision-making.

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