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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, so the safety profile is covered; the description adds genuinely new behavior: runtime expectation ('takes a few seconds'), the shape of the response ('the summary, each habitat's result and the best solution'), and a persistence guarantee ('Nothing is saved to your projects'). It does not cover failure modes (e.g., invalid protect ids) or whether the run is deterministic across `reps`, which keeps it off a 5.

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 sentences, front-loaded with what the tool produces before the parameter glossary. Every clause carries information — scope, output, parameter meaning, runtime, and side-effect — with no restatement of the name or title.

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 read-only, three-parameter compute tool with no output schema, the description supplies return shape, runtime, and a no-persistence guarantee, which is nearly everything an agent needs. The remaining gap is error/edge behavior (invalid protect ids, behavior when target_pct is omitted).

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% (only `reps` is documented), so the description must carry the load — and it does, explaining that `protect` takes planning-square ids sourced from understand_area's `pus` and that `target_pct` is a single percentage applied to every habitat. The non-obvious Marxan semantics of these two params are precisely what the schema omits; only edge details like default/empty `protect` behavior are unstated.

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+resource (run the Marxan optimiser on the example project's planning data) and glosses the output in plain language: 'the cheapest set of planning squares that meets every habitat target.' The scope restriction (Exmouth Gulf, Western Australia only) makes it unmistakable against siblings like get_project or understand_area, which read data rather than run an optimiser.

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?

Establishes the applicable context clearly ('example project's planning data ... Western Australia only') and points the agent at understand_area as the source of `pus` ids for `protect`, which is real workflow routing. It stops short of an explicit when-not-to-use or a named sibling alternative for the same goal, so it is clear but not exhaustive.

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