telys_search

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

Annotations already declare readOnly, idempotent, and non-destructive, and the description adds valuable behavioral detail beyond them: the server embeds the query on-device, results come from 'live rows', and the tool returns isError for missing collections or multi-key `where` filters. This gives the agent concrete expectations about execution and failure.

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?

The description is dense but every sentence earns its place: purpose and mechanics, intended usage, required/optional parameters with example, and failure modes. The most decision-relevant information is front-loaded before parameter details, with no filler or repetition of the schema.

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?

Despite having no output schema, the description covers return shape (hits with id, score, metadata), required and optional parameters, a filter example, and error behavior. For a read-only search tool with supporting sibling tools, nothing essential is missing for an agent to select and invoke it 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 only 25%, but the description compensates thoroughly: it explains that `query` gets embedded, that `top_k` defaults to 5, and that `where` is a single-key equality filter with a concrete example (scope=project:acme). It also flags required vs optional parameters and the failure condition tied to `where`, making every parameter actionable.

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 opens with a specific verb and resource: 'Semantic + lexical search over a Telys memory collection.' It then explains the execution model (embedding `query` and returning best-matching hits) and names the return fields (id, score, metadata), making it clearly distinguishable from siblings like telys_search_lexical and telys_repo_search.

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 a clear use context: 'Use to recall stored notes/facts/decisions before answering.' It also provides an exclusion path by stating the tool fails when the collection does not exist and directing the agent to write first via telys_add or telys_create_collection. It stops short of explicitly contrasting with telys_search_lexical, so it earns a 4 rather than a 5.

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