Search Ontology

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

Annotations already establish readOnly, non-destructive and closed-world, so the safety profile is covered. The description adds genuine context beyond them: it enumerates which object classes are searchable, discloses that stored record text surfaces as 'value' hits, and notes that another datasource's data can be reached via kind 'value'. It omits anything about ranking, result ordering, or how limit truncation behaves.

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 sentences, front-loaded with the scope enumeration and closing with the actionable 'Not semantic' directive. The middle sentence is heavy with a parenthetical that packs two ideas together, costing some readability, but nothing is padding.

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 no explanation, and all four parameters are documented in the schema. The description supplies the remaining conceptual layer — what corpora are searched and what the 'value' kind does — which is what an agent needs to call this 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 100%, so the baseline is 3; the description pushes above it by explaining that kind 'value' is the mechanism for searching a different datasource's data and by characterizing the query string as business nouns, metrics, columns or values with synonyms/translation encouraged. The datasource/kind interaction is clarified in prose rather than left purely to the schema.

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 opening sentence names a specific verb (lexical search) and enumerates the resource scope precisely: terms/concepts with bodies and relations, synonyms, mapped columns, SQL attributes, glossary, verified example questions, sources and unmodeled tables. It also declares what it is not ('Not semantic'), which separates it from any semantic-retrieval path, though it never names the concrete siblings (list_terms, get_term, lookup_values) that overlap its scope.

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 guidance is strategy-oriented rather than routing-oriented: 'use the schema's vocabulary, try synonyms, translate' tells the agent how to phrase a query, and the 'value' hint tells it how to reach another datasource's records. There is no explicit statement of when to reach for this tool versus list_terms/get_term/lookup_values, so the agent must infer the boundary from the enumerated scope.

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