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

Annotations already declare destructive/non-idempotent/non-readOnly, and the description adds real side-effect detail beyond that: warp moves ALL members at once, fight requires every member on the same pirate_id in the SAME sector, target_id=0 clears the lock. It does not say whether disband or leave is reversible or what the fleet state becomes after a leader leaves, which for a destructiveHint=true tool is a remaining gap.

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?

Front-loaded with scope and the exclusion first, then a dense but information-bearing action list where every clause carries a permission or effect. The parenthetical chains are hard to scan for 12 actions, but no sentence is padding.

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 12-action, 9-parameter destructive dispatcher, the description covers permissions, cross-member side effects and per-action preconditions well. It stops short on failure behavior (what happens when a non-member is invited, what a fleet looks like after disband) and there is no output schema to carry return-value context.

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% and each parameter already carries its own 'For <action>' note including the mode enum and the target_id=0 convention, so the description mostly restates it. The only value added beyond the schema is the get_sector cross-reference for finding pirate_id and the fact that action accepts exactly those 12 values.

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?

Names the resource (corp fleet of several pilots), states that dispatch is via the action parameter, and enumerates all 12 actions with their effects. It also explicitly carves out the nearest confusion point ('Not for your own ships -- that is execute_action SWITCH_SHIP'), so an agent can separate it from execute_action without opening a 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?

Gives explicit gating conditions per action (leader only, CEO/DIRECTOR to create, Admiral T3 for create/warp), plus a sequencing hint ('invites -- read before accept/decline'). It never routes to the sibling `warp` or `attack` tools, even though the fleet warp/fight actions sit adjacent to them in name and function, so one ambiguity remains.

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