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

Annotations cover only the safety profile (readOnly/openWorld/non-destructive), and the description adds substantial behavioral context beyond that: the fleet_cap scan ceiling, the fact that unfiltered counts are WORLD counts rather than US counts (21.6% international), that spec filters exclude aircraft lacking values, and that the `country` filter is rejected by the v3 validator and cannot select international aircraft. For a read-only aggregation tool this is unusually rich disclosure of data-quality and scoping behavior.

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 purpose, use case, and mechanism in the first three sentences, and the dense warning blocks are formatted with headers and emoji anchors. However, the filter-grammar material is exhaustive to the point of overlap with the schema, and the registry-fleet caveats are restated more than once, so it is longer than strictly necessary.

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?

An output schema exists, so return values need not be explained in prose, yet the description still names the fields to read (total_count / state_counts). Combined with the filter-grammar guidance, the fleet_cap limit, and the international-registry caveat, an agent has everything needed to call this correctly and interpret the number.

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 already 100%, so the baseline would be 3, but the description adds genuine semantics beyond the schema: union vs AND semantics for `make_model_id` (use `in` with an array, never repeated clauses), the `within_<miles>` + "lat,lon" pattern for location_point, the registry-authority code/token list, and population percentages for each sparse spec field. It also explicitly resolves a naming ambiguity (no `country` filter, use registration_country).

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+resource: 'Aggregate registry census for a filter set: the total number of matching aircraft plus breakdowns by US state and by build year.' It explicitly contrasts itself with the sibling search_aircraft by noting it works 'without paging individual tails,' so an agent can route between counting and listing without opening either 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 a concrete use case ('how many Cessna R182s are registered in Oregon' with the exact filter shape), states it reuses 'the same filter grammar as search_aircraft,' and calls out the boundary condition that counts are computed over up to fleet_cap aircraft. It also tells the agent when NOT to repeat a filter ('Do NOT repeat make_model_id in separate clauses') and to warn the user when sparse-coverage filters are used.

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