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

With only readOnlyHint=false in annotations, the description carries the full burden and delivers: it discloses that recruiting draws from shared pools and the faction treasury, that withdrawals are gated on ManageTreasury, and that transfers force the active ship to retain one fit crew member. These are precisely the side effects and constraints an agent needs to predict, far beyond what the annotation conveys.

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 purpose verb phrase is front-loaded and every clause in the dense parenthetical earns its place with zero filler. The single run-on parenthetical is information-heavy enough that bulleted or sentence-separated constraints would be easier for an agent to parse, though no content is wasted.

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 6-parameter, 4-action mutating tool with no output schema, the description fully covers prerequisites, permissions, and side effects but omits the meaning of the four personnel-count parameters and says nothing about what status/deposit/withdraw return. Since there is no output schema to fall back on, those gaps leave an agent guessing about both inputs and responses.

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 33% (session_id and action carry descriptions), yet the description never explains the four numeric parameters fit_crew, fit_marines, injured_crew, and injured_marines. The prose adds meaning to the action values (recruit drains treasury, deposit/withdraw permission split) but leaves the count parameters ambiguous — an agent cannot tell whether they are inputs, expected states, or return filters.

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 specific verb-resource pair — 'View, recruit, or transfer personnel held in your faction's local reserve' — that maps onto the status/recruit/deposit/withdraw enum. The docking qualifier ('station where your faction operates a personnel reserve') scopes it away from siblings like recruit_personnel and transfer_personnel, so an agent can discriminate without opening 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 states the precondition explicitly (must be docked at a faction reserve station) and gives per-action permission rules: ManageTreasury required for recruit and withdraw, deposits open to all members, transfers require being out of combat. It stops short of naming alternative tools or explicit when-not-to-use conditions, which is the only gap keeping it from a 5.

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