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

Goes well beyond the annotations by disclosing that it is a MUTATION, that it costs one AI-gateway operation per field per page (up to 20), that there is no bulk discount, that partial failures are isolated per entry, and that org-admin rights are required. This is rich behavioral context an agent could not derive from readOnlyHint/destructiveHint alone.

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?

Dense but front-loaded narrative where every clause earns its place: purpose, cost, failure isolation, and prerequisite in a handful of sentences. No filler or redundancy.

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 non-idempotent mutation tool with no output schema, the description covers the critical gaps: cost model, partial-failure behavior, and authorization requirement. Nothing an agent needs in order to call it correctly 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?

Schema coverage is 100%, so both params are already documented (pageUrls with its 1-10 range and projectId with the list_projects pointer). The description's 'up to 10 pages' restates the schema's maxItems constraint rather than adding new syntax or format meaning, so baseline 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 and resource ('AI-drafts title AND metaDescription') with a clear scope ('up to 10 pages in one call'), which inherently distinguishes it from the single-page sibling draft_patch. An agent immediately knows this is the batch variant.

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?

Gives strong usage context: batch-of-up-to-10, cost implication (one operation per field per page), and a prerequisite ('Requires an org admin'). It does not explicitly name draft_patch or state when to prefer one over the other, so it's clear context without explicit alternatives.

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