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

Annotations already cover readOnly/idempotent/non-destructive, and the description goes well beyond them: it discloses the exact checks performed, that red_line_upload confidence is assigned only when every blocking check passes, the four accepted CRSs, and — critically — that the uploaded geometry is not persisted. That non-persistence note is the kind of surprise an agent would otherwise be ambushed by.

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?

Explicitly labelled sections (Purpose / When to use / Returns / Limitations / Parameter guidance / Chaining) make it scannable, and purpose is front-loaded first. The 'Returns' enumeration is long and partly duplicates the output schema, which costs a point on conciseness.

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 geometry-validation tool with a nested site_ref object and four CRS options, everything an agent needs is present: accepted inputs, CRS whitelist, failure semantics for confidence, non-persistence, and the chaining contract. The output schema covers return shape, so no further expansion is required.

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, but the description adds real meaning: boundary_geojson should carry a Feature or geometry, source_crs must be declared explicitly, declared_area_m2 is only for a mismatch check, and site_ref should be passed unchanged to retain address, LPA and project context. The chaining semantics of site_ref are genuinely beyond the schema.

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 ('check a user-supplied red-line boundary before treating it as the site geometry') and situates it relative to siblings by naming Site Verdict and focused constraint checks. An agent can tell this apart from analyze_site or check_planning_constraints without opening any 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 'When to use' sentence gives a clear trigger ('after receiving a GeoJSON Polygon or MultiPolygon') and ordering pressure ('especially before Site Verdict'). The Limitations section implicitly rules out title, ownership, survey accuracy and planning-conclusion uses, but there is no explicit 'do not use this when…' statement.

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