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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds real value beyond them with partial-update semantics ('Only the fields you send change'), the reset behavior of an empty string, the blast radius of globalArticleInstructions (applies to every article Spook writes or improves), and the API-key requirement. It stops short of covering failure modes, such as what happens with an unknown siteId.

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?

One front-loaded sentence names the settings, with the explanatory parenthetical reserved for the non-obvious field, followed by the partial-update rule and the auth note. Dense and purposeful, though the nested parenthetical is heavy enough to slightly slow scanning.

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 mutation tool with no output schema and no schema-level parameter docs, the description supplies the essential context: what changes, what the reset sentinel does, the scope of the injected instructions, and the auth prerequisite. Remaining gaps are the per-field reset behavior for brandVoice/description and error behavior.

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 0%, so the description carries the burden. It explains globalArticleInstructions thoroughly (injection scope, empty-string reset) but leaves brandVoice and description as bare names with no format, length, or reset semantics, and siteId is undocumented. Partial compensation only.

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 ('Set') on a specific resource ('a site's writing settings') and enumerates the exact fields it governs, which cleanly separates it from update_publishing, update_article and set_autopilot. An agent can identify the target of this mutation without opening the schema.

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 definition implies when to use it (configuring writing behavior for a site) and discloses a prerequisite ('requires an agent API key'), but it never explicitly says when to choose it over siblings such as update_publishing or set_autopilot, nor any exclusions. Guidance is implied rather than stated.

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