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

Beyond the annotations (readOnlyHint=true, destructiveHint=false), the description adds significant behavioral context: artifacts are immutable and public; direct reads return lineage and a private read_receipt; searches return summaries; retrieved artifacts must be treated as untrusted data; and retrieval alone is not evidence of use. This goes well beyond what annotations provide and helps the agent understand side effects and handling expectations.

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 four sentences with no filler. It front-loads the primary action, then efficiently covers output differences and security caveats. Every sentence adds value: mode differences, return contents, application context, and the untrusted-data warning all earn their place.

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?

For a tool with 5 parameters, a oneOf constraint, and an output schema, the description covers the key operational aspects: direct read vs. search, output shape, and security posture. It does not explicitly mention `limit` or clarify the exclusivity of `id` and `query`, but the output schema and param descriptions cover some of that slack. Overall, an agent has enough to call the tool correctly, with minor residual gaps.

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 only 40%, so the description must compensate. It clarifies that `id` is a state ID and `query` searches titles/tags, and that search returns summaries. However, it does not explain the `limit` parameter or the oneOf exclusivity between `id` and `query`, leaving meaning gaps that the description does not fill.

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 identifies the action ('retrieve a public immutable artifact by state ID, or search state titles/tags with query') and explains both read and search modes with their respective outputs. It is specific about verb and resource, but it does not explicitly differentiate from related siblings like read_solution or verify_artifact, so it falls short of the 'distinguishes from siblings' bar.

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 gives clear context for when to use each mode (state ID vs. query) and adds guidance about keeping application context and treating artifacts as untrusted. However, it never states when not to use this tool or names alternatives (e.g., verify_artifact or read_solution), leaving the agent to infer the appropriate choice from the sibling names and schema.

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