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

Annotations only declare the generic mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false). The description adds substantial non-obvious context: leading to or withdrawn being excluded, later additions staying out, that every public read re-checks base publication, that private/withdrawn collections return 404, and that responses are private, no-store. This is exactly the extra behavioral disclosure the annotations do not carry.

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?

Front-loaded with the core action and dense with useful detail, but several sentences (e.g. 'Owner search reads current files in owned bases and published files in other bases') sit somewhat apart from the publish action. Slight looseness keeps it below a 5.

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 one-parameter mutation tool with annotations and no output schema, the description covers the important edge cases (404 on private/withdrawn, no-store caching, what is and isn't included). An agent has enough to invoke it correctly.

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 100% and there is a single required parameter (collection_id), so the schema already carries the parameter meaning. The description adds no format or identity details beyond what the schema states, so the baseline of 3 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+resource ('Publish references to currently public bases') and clarifies what publication does semantically (references, not copied content). An agent can distinguish it from create_collection or remove_collection, though it never names the inverse sibling unpublish_collection explicitly.

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 establishes the state model ('They start private', publication includes only references to currently public bases), which implies when to publish, but it never states explicit when-to-use criteria or points to alternatives like unpublish_collection. Usage must be inferred from the behavioral model.

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