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

Beyond the readOnly/idempotent/closed-world annotations, the description discloses the actual matching algorithm (shared use category via keywords/NAICS, or two-plus shared words / all significant words of the restriction), the output labelling ('potential conflict — needs human review'), what each hit returns, and that carve-outs mentioning the proposed use are flagged. It also states hard limits — deterministic and textual, no interpretation, no legal conclusion, false negatives possible — which is exactly the behavioral context annotations cannot supply.

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?

Purpose is front-loaded in the first clause and every subsequent sentence carries operational weight — matching rules, labelling, return payload, limitations. It is a single dense block with some redundancy (the deterministic/textual caveat appears twice in effect, and matching criteria are restated in the parameters), so it is efficient but could be tightened or broken into structure.

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?

There is no output schema, and the description compensates by describing the return payload: controlling quote, citation, matched categories and words, and flagged carve-outs. Combined with the stated limitations and prerequisites, an agent has everything needed to call this correctly and interpret an empty result without over-reading it.

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so baseline is 3; the description adds real meaning on top: which predicates are consumed and which are skipped, that superseded facts are dropped, the fact_validate precondition, and NAICS prefix-matching breadth (7225 matches restaurants and coffee shops). It largely restates the vocabulary and matching hints already in the schema property descriptions, which keeps it from a 5.

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 proposed use against a center's verified lease.exclusive_use and lease.prohibited_uses facts — and names the tool's role in a pipeline (consumer of doc_verify_facts / doc_abstract_lease output) rather than a generic 'check'. An agent can distinguish it from doc_verify_facts or fact_validate without opening the 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 description gives clear entry conditions: facts must come from doc_verify_facts or doc_abstract_lease and each must pass fact_validate, and superseded facts are ignored. It also sets expectations about scope (no lease interpretation, no legal conclusions, empty result is not a clearance). It stops short of naming a concrete alternative tool for cases outside its scope, but the preconditions are explicit enough to route correctly.

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