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

Annotations supply only readOnlyHint=false, so the description carries the real weight and does: it states where the removed module lands (ship cargo, with station-storage fallback when cargo is full and service exists), and enumerates the specific failure codes cpu_exceeded, power_exceeded, and cargo_capacity_exceeded plus the asymmetry that capacity-costing modules are never refused. That is exactly the kind of consequence detail an agent cannot infer from structured fields.

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 core action and the ship_id default are front-loaded, and each subsequent sentence covers a distinct concern (host ship eligibility, module_id forms, docking prerequisites, cargo-fit math, refusal rules). It is a dense single paragraph, and a few clauses restate what the schema already documents, but nothing is filler.

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 three-parameter mutation with no output schema and only a readOnlyHint, the description covers destination of the removed item, eligibility of the target ship, ID format ambiguity, cargo-capacity edge cases, and the exact refusal conditions. An agent has enough to call this correctly and to anticipate failures.

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 baseline is 3; the description earns above that by explaining that module_id accepts either a module instance ID (from get_ship) or a type ID like 'pulse_laser_i', and that duplicate types force the instance ID. It also clarifies that ship_id may be omitted or left empty for the active ship, though that point largely duplicates the schema's own ship_id text.

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?

Opens with a specific verb and resource — "Uninstall a module from your active or stored ship" — and immediately scopes the two variants (active vs. stored) that matter to the caller. The verb is the natural inverse of the sibling install_mod, so an agent can pick between them without inspecting schemas.

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 preconditions (must be docked, need a Ship Maintenance Bay, or be at the same POI as an undocked faction-mate with one) and names the valid host ships plus the exclusions (faction garage, carrier, tow, exchange listing). It also tells the agent what to do when refused ("unfit a consumer first"). The one gap is that it never explicitly says to use install_mod for the reverse operation, leaving that routing to the name alone.

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