add_agent_seat

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

With no annotations, the description carries the full burden and it delivers the single most important behavior: the pb_ API key is returned once with no retrieval path, plus the owner/tier authorization constraint. It stops short of stating whether the seat is revocable or whether the key can be rotated, which would matter for this mutating operation.

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?

Two tightly packed sentences with zero filler. The action and its authorization gate come first, and the irreversible secret-return warning is front-loaded where it cannot be missed.

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 small mutating tool with no annotations and no output schema, the description covers action, authorization, and the critical one-time secret return. The remaining gap is the undocumented `projectId` and what happens on repeat calls for the same project.

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 only 50%: `name` is documented in the schema, but `projectId` has no description anywhere. The phrase "on a project" hints at project scoping but never clarifies how projectId is supplied or whether omitting the optional-looking parameter falls back to a default context.

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 ("Mint an agent seat on a project") with a clear scope qualifier. No sibling tool competes with this action (invite_contributor, list_members, revoke_member all concern humans/contributors, not agent seats), so an agent can uniquely identify it.

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 real preconditions for use — "owner only, Team tier" — which tells the agent when the call will be permitted. It does not name alternatives or explicitly say when not to use it, but no sibling is a plausible substitute, so the omission is minor.

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