entitlement_add

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

It discloses behavior beyond annotations: a bare call returns blast_radius and grants nothing, confirm=True grants, the tool refuses when entitlements cannot be read, and it is audited. It also includes an important safety directive: do not set confirm=True on your own because the user has not yet seen the blast radius. No contradiction with the annotations is present.

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 compact and front-loaded: the purpose appears in the first sentence, followed by essential workflow and safety guidance. Every sentence earns its place, including the final 'Audited.' There is no repetition of schema details or unnecessary elaboration.

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?

Despite having no output schema, the description explains the return behavior of a bare call (blast_radius with pool identity, existing vs new principals) and the effect of confirm=True. It covers the key prerequisites, the refusal edge case, and the required user interaction step. This is sufficient for an agent to select and invoke the tool correctly.

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?

The schema already covers all parameters at 100%, and the description adds meaningful context: ad_user_or_group_ids are SIDs from ad_user_search, pool_id comes from pool_list, and confirm=False/default returns blast_radius while confirm=True grants. The blast_radius explanation ('which principals are already entitled and which are new') adds value beyond the schema descriptions.

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 opens with a clear verb and resource: 'Grant desktop-pool access to AD user/group SID(s).' It also clarifies the write nature with '[WRITE]' and names the exact entity being modified, distinguishing it naturally from entitlement_remove. The scope is specific enough that an agent can understand what this tool does without inspecting 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 description gives strong usage workflow: get SIDs from ad_user_search, call without confirm to see blast_radius, show it to the user, wait for their decision, and do not auto-confirm. It also states a refusal condition. It stops short of explicitly naming alternatives such as entitlement_remove, but the 'Grant' phrasing and sibling list make the use case clear enough.

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