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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds genuinely new behavioral context: corpus size and the shape of results (records with tiers, passages with excerpts). This matters because there is no output schema. It doesn't touch pagination, ranking, or how limit interacts with the two result types.

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?

Three short sentences, front-loaded with scope and result shape, with no filler. The sentence 'Returns records with their tiers and passages with excerpts' is dense but earns its place since no output schema exists; 'the master' is slightly opaque terminology.

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 and only 50% param coverage, the description should carry more weight. It covers scope and result categories but leaves the limit semantics and any ranking/ordering behavior unexplained, which an agent needs to interpret a two-type result set correctly.

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 50%: 'query' is documented, but 'limit' (default 8, max 20) has no schema description and the tool description never explains it — notably whether it caps records, passages, or the total, which is a real ambiguity. The quoted-phrase note does add meaning beyond the schema's terse 'Words or a quoted phrase'.

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?

The description names a specific verb (Search) and resource (the whole public record, 4,700+ records plus the master's full text), and states what is returned (records with tiers, passages with excerpts). It implicitly separates itself from sibling read tools like parse_read_record and parse_read_passage, though it never names them.

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?

Usage is only implied: searching when you don't have a specific record/passage versus reading one directly. The only explicit guidance is query syntax ('Quotation marks keep a phrase exact'), which is useful but is parameter guidance rather than when-to-use guidance. No alternatives or exclusions are named.

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