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

With no annotations provided, the description fully discloses the tool's behavioral traits. It states that the tool only stages a request (not directly applying the change), that the owner must approve via a browser link with their PIN, and that owners always have edit access. This covers side effects, async nature, and security handling, exceeding typical disclosure.

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 description is concise at roughly three sentences, front-loading the core purpose before explaining levels and the approval flow. Every sentence adds value—no fluff or repetition. The structure is logical, moving from what the tool does to the three levels to the behavioral caveat and security 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?

Given the tool's complexity (4 params, one enum, no output schema, no annotations), the description is thorough. It covers the semantics of each level, the staging and approval process, the PIN security rule, and references to related tools for slugs and updates. Nothing essential for correct invocation 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 description coverage is 100%, so the baseline is 3. The description adds meaningful elaboration on the enum values (none, use, edit) beyond the schema's brief descriptions, and it clarifies that list_skills provides the slug for the skill parameter. It also reinforces the workspace parameter's conditional necessity, though that is already in the schema. This adds value but not extensively beyond the schema.

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 clearly states the tool's purpose: setting an access role's level of access to a specific skill, with explicit definitions of the three levels (none, use, edit). It distinguishes itself from related tools by referencing update_skill for edit-level changes and list_skills for slugs, though it doesn't name a direct sibling like set_access_role_capability. The verb 'set' and resource 'access role's access to a skill' are specific and unambiguous.

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 description provides clear usage context: it explains the levels, notes that 'use' is the default, and warns that the tool only stages a request requiring owner approval. It also explicitly instructs to never ask for or accept the PIN in chat. However, it does not explicitly contrast with alternative tools like set_access_role_capability or set_access_role_mailbox_access, though the naming and focus make the intended use fairly obvious.

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