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

Annotations already declare destructiveHint=true, and the description adds material context beyond them: owner-token authorization, accepted payload shapes, and the exact failure mode (409 OLD_PUBLICATION_READ_ONLY with a createUrl). It doesn't clarify whether the write is a full replacement or a merge, which is the one missing behavioral fact for a destructive mutation.

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?

Three compact sentences: purpose first, then the auth prerequisite, then the payload shapes and the legacy-document edge case. Nothing is padded, though the payload-shape clause slightly duplicates the schema.

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 destructive mutation with no output schema, the description covers authorization, accepted input forms, and the legacy read-only failure plus its remedy. The replace-vs-merge semantics of 'update' are the only notable omission.

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%, so all four parameters are already documented, including ownerToken's default of BREWPAGE_OWNER_TOKEN. The description's note about accepting object, array, or JSON-encoded string restates the anyOf in the schema rather than adding meaning.

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?

A specific verb (update) and resource (BrewPage JSON document) plus the fact that it targets an existing document, which implicitly separates it from publish_json. It stops short of naming the sibling to use for new publications, so differentiation is inferred rather than stated.

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?

It states the prerequisite (owner token) and, crucially, the condition under which the tool cannot be used: documents published before 5 October 2026 are read-only, with createUrl to publish anew. That is real routing guidance, though it doesn't explicitly say 'use publish_json for new documents'.

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