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

Annotations already declare idempotentHint=true, destructiveHint=false, and openWorldHint=false. The description adds two things not in the structured data: the required owner/admin authorization level and the fact that no credential is returned, which is useful for an agent expecting a token back.

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?

Three short sentences, zero padding, with the action stated first and the auth prerequisite and return behavior immediately after. Every sentence carries distinct information.

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?

Covers the action, the authorization requirement, and the absence of a credential for a mutation with no output schema. It omits what happens if access already exists and how failures surface, but the idempotent annotation partially covers replay 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 coverage is 100%, so projectId and idempotencyKey are fully documented in the schema, including the reuse-key-on-timeout rule. The description adds no parameter-level detail beyond that, so the baseline of 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 (store/provision) and resource (project-scoped EDITOR access on a dossier), so an agent knows this grants a permission grant rather than preparing or confirming one. It stops short of distinguishing itself from the cluster of sibling tools like prepare_dossier_access, apply_dossier_library_access, and confirm_dossier_access.

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 prerequisite 'Requires a workspace owner or administrator' gives a real eligibility condition for calling it. However, it gives no guidance on when to use this store step versus the prepare/apply/confirm access siblings, so the sequencing is left to inference.

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