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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description's one added fact — there is no closed enum, so `type` values are agent-invented — is genuinely useful and non-obvious behavioral context, but it stops there, with no guidance on validation, naming collisions, or how invented types are interpreted downstream.

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 short sentences, front-loaded with the resource and immediately followed by the single caveat that matters. Nothing is padded or repeated from the name.

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 zero params, a present output schema, and full annotation coverage, the description supplies the one thing structured fields cannot: that `type` is open rather than enum-bound. Only a pointer to sibling discover_* tools for adjacent catalog needs is missing.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies.

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?

States a specific verb (describe) and specific resource (the `resolutionSource` envelope shape plus the conventions agents use), which is more precise than a generic catalog listing. It doesn't explicitly contrast itself with the other discover_* siblings, but the resource is named concretely enough that an agent knows what it returns.

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?

Usage is only implied: the note that agents invent their own `type` values suggests this should be consulted before constructing a resolutionSource, and the 'discover' prefix implies a pre-flight lookup. There is no explicit when-to-use/when-not statement nor a named alternative for related questions.

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