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

The description discloses the underlying mechanism (BGE-base-en embeddings, cosine, 500-char overlapping windows), the output format (character offsets and similarity scores), and truncation behavior with a 200K char cap and flagging. This goes well beyond the annotations which only indicate read-only/idempotent, adding meaningful operational context.

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 front-loaded with the core action and delivers additional detail in compact sentences. Every clause earns its place: the usage scenario, the pairing, and the technical specifics are all relevant and non-redundant.

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?

Given the absence of an output schema, the description thoughtfully covers return values (passages with offsets and scores), input constraints (text cap and truncation), and integration with sibling tools. It provides enough for an agent to correctly select and invoke the tool.

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 adds context beyond the schema: 'Pass the text you already pulled' clarifies that `text` is a pre-fetched record, and 'get back the top-N passages' directly maps to `limit`. It also provides example queries, but the schema already documents parameter meanings thoroughly, so only a modest improvement.

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 explicitly states 'Semantic search INSIDE a fetched record', specifying the verb (search) and resource (a fetched record). It distinguishes from siblings by noting it 'Pairs with ask_pipeworx_grounded' and implies a workflow of fetching then searching inside, clearly separate from other sibling tools that do broader research or grounding.

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?

It provides explicit usage guidance: 'Use when the record is too big to cram into the prompt' and describes the pairing: 'Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document.' This tells the agent not only when to use but also how it relates to an alternative/complement.

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