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

Goes well beyond the annotations (destructiveHint=true, idempotentHint=false) by disclosing optimistic-concurrency behavior via the revision, permission requirements, and partial-update semantics ('Omitted fields are preserved; supplied menus replace that menu'). It also flags that header/footer HTML is executed as custom code, a non-obvious risk. It does not state reversibility/undo, which is the only remaining gap.

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?

Five short sentences, front-loaded with the action and the user-consent constraint, then the precondition, then the field semantics. No filler and nothing buried at the end.

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, non-idempotent mutation with a deep nested settings object and no output schema, the description covers the essentials: consent, permissions, revision, merge-vs-replace, and image sourcing. It leaves the response behavior and recovery from a stale revision unspecified.

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 50%, and the description compensates partly: it explains that revision must come from get_blog_settings, that omitted fields persist, and that menus are wholesale replacements. Those replacement rules are also repeated in the schema for the menu fields, and the many scalar settings (timezone, copyright, banner fields, toggles) get no added meaning from the description.

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?

Specific verb+resource ('Change blog settings ... on the live blog') with scope made explicit ('immediately', 'live'). It is clearly distinguishable from the read-only sibling get_blog_settings, which it names as a prerequisite.

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?

States the gating condition ('only when requested by the user'), the required permission set, the mandatory workflow ('Read get_blog_settings first and supply its revision'), and routes image sourcing to upload_asset. When-to-use and prerequisites are both covered without inference.

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