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

Annotations already declare a safe, idempotent read, so the bar is lower, and the description still adds real semantics: a 25-result cap, total_capped as a lower bound, total_unknown as an indeterminate total, source-level data_through freshness, and the warning that an empty result is not proof of absence. It does not cover auth, rate limits, or how _notes is surfaced, keeping it from 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?

Front-loaded with the core action and filter dimensions, then dense caveats, with no filler sentences. The trailing pointer to _notes is useful but slightly dangling since its content is not described inline.

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 23-parameter, no-output-schema search tool, the description covers result limits and total-count semantics that the schema cannot express, which is the main completeness gap. Remaining gaps are minor: no guidance on which filter combinations are required or how sparse coverage affects narrow queries.

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?

With 23 parameters at 65% schema coverage, the schema carries most of the semantics, including enums and defaults. The description adds only coarse groupings (place, type, status, dates, proposed size) and does not clarify the page vs start interaction or the lat/lng plus radius_miles pairing beyond what the schema already says.

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 (search planning and zoning cases) and enumerates the filterable dimensions: place, type, status, dates, proposed size. It is clearly narrower than the sibling decision/certificate/permit searches, though it does not name get_pipeline_case as the single-record counterpart, so an agent must infer that distinction.

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 sets important expectations about coverage and empty results, which implicitly tells the agent when this search is trustworthy, and it points to _notes for pagination. It never states when to prefer this over a sibling such as search_pipeline_decisions, nor does it flag the zero-required-parameter breadth as something to constrain.

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