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

Annotations only cover the read-only/idempotent profile, yet the description adds real behavioral context: exact-match/no-stemming semantics, coverage counts including 1,798 unsearchable records, the 2026-09-30 corpus cutoff and how to interpret empty results, freshness metadata fields (body_as_of, body_pending), and a transient 503 with one retry. That is substantially more than structured fields provide.

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: the first sentence pins down mechanism, scope, and the keyword-vs-concept distinction before any caveats. It is dense but not padded, though the long coverage-statistics and freshness-metadata passage makes it heavier than a selector strictly needs.

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?

With no output schema, the description takes on the burden of explaining returns and does so (opinion_id, cluster_id, BM25 rank, case metadata, highlighted snippet, plus the per-response 'note' and body freshness fields). For a 7-parameter search tool on a finite mirror, an agent has everything needed to call and interpret 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 description coverage is 100%, so baseline is 3. The description restates the 'q' semantics already present in the schema (all words must appear, no stemming, quotes for phrase) and says nothing about court, limit, date bounds, min_citation_count, or precedential_status, so it adds little beyond structured data.

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 ("Keyword full-text search (BM25) over opinion body text") and immediately contrasts itself with the conceptual sibling semantic_search. An agent can distinguish it from semantic_search 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?

Explicitly says when to use the alternative ("A case that states the concept in other words does not appear; semantic_search covers that gap") and warns about misreading thin results near the collection cutoff. It does not, however, differentiate from the plainer sibling 'search', which an agent must still infer about.

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