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

Beyond annotations (destructive, idempotent, open-world), it discloses concrete side effects: renaming preserves slug/URLs, disabling the public page immediately makes publicUrl 'not found' while leaving document links intact, enabling it lists documents with active links, and duplicate names produce a validation error. It also warns that result titles and viewer text are untrusted.

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?

The paragraph is front-loaded with the three actions and the core partial-update rule, then progresses through side effects and validation. Every sentence carries distinct, useful information, including the final untrusted-content warning.

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 with no output schema and rich annotations, the description supplies the missing behavioral context: partial update semantics, unique-name validation, URL/slug preservation, public-page toggling consequences, and a trust warning on returned text. No critical gap remains for safe invocation.

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 the baseline is 3, but the description adds meaning beyond the schema for name (validation error on duplicate), description (clearing effect implied by schema empty string), and publicPageEnabled (exact publicUrl behavior and document listing effect). The projectId/projectSlug alternatives remain schema-documented 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?

The description states specific actions and resource: rename a project, change its description, or toggle its public page. It names the exact field publicPageEnabled and distinguishes this from create/delete siblings by focusing on partial updates.

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 clearly explains the partial-update contract: at least one field required, anything not passed is kept. It does not name alternative tools (e.g., create_project or delete_project) or explicitly say when not to use it, but the update context is unambiguous.

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