locate_evidence

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

With no annotations, the description carries the behavioral burden and does so well: it says the ranker can only select passage/sentence identifiers from text, that Entroly derives returned text/offsets/hashes from the original source, and that invalid ranker output abstains. This discloses meaningful behavior beyond the schema.

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 three focused sentences with the main purpose front-loaded, followed by two dense behavioral constraints. No filler or redundancy.

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?

Although an output schema exists and covers return values, the tool takes 7 parameters with zero schema descriptions and no annotations. The description leaves key parameters and their defaults unexplained, so it is not complete enough for confident invocation.

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 0%, so the description must compensate, but it only adds limited meaning around text as the original source. The seven parameters include min_score, max_matches, passage_mode, source_id, and calibration_id, none of which are explained in the description.

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 specific action 'locate exact source spans' and adds the key constraint 'without generating an answer', which distinguishes it from answer-generation siblings. It does not explicitly name a sibling alternative, but the scope is clear enough.

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 context is implied: call this when you need source spans from provided text and no narrative answer. It does not explicitly state when to prefer it over siblings such as entroly_retrieve or recall_relevant, nor list exclusions.

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