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

Annotations only cover the safety profile (non-read-only, non-destructive, closed-world). The description adds real behavioral context beyond that: role restriction to owners/admins and a cap of 10 active cockpits. It doesn't mention the preview/confirmation flow that the schema's confirm_id implies.

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, front-loaded sentences with no filler; the create/update rule leads. Each sentence carries a distinct fact (mode, authorization, parameter sourcing, limit).

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 tool with no output schema, the description covers mode selection, authorization, and the active-cockpit limit. The confirmation-token workflow is left to the schema, which is acceptable, though it leaves return behavior unspecified.

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 only 17%, so the description must compensate. It does document cockpit_id (create/update switch), outpost_ids (source and omit=all semantics), and status values, but leaves name and description undocumented; a baseline 3 is appropriate given partial compensation.

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: create or update a cockpit of the user's organization, and clearly ties the create-vs-update branch to the presence of cockpit_id. It doesn't name siblings like get_cockpit or list_cockpits explicitly, but an agent can still tell it apart.

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 explicit conditions: create when cockpit_id is absent, update when present; owners/admins only; max 10 active cockpits. It also tells where to source outpost_ids (list_clients) and what omission means. It stops short of naming an alternative tool for read operations.

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