Dossier Evidence

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that the tool is asynchronous (returns a task number), runs separate sessions per source, and verifies quotes against source text. However, it omits how to poll for completion, auth/permission needs, failure behavior, and whether repeated calls create new jobs.

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?

Two dense sentences front-load the primary action and return value, then enumerate the card contents. There is no filler, though the second sentence is a long enumeration that could be slightly tighter.

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-card fields need not be fully explained, and the description does note the task-number return. Still, for an asynchronous generation tool with no annotations and 0% parameter coverage, critical gaps remain around parameter meaning and how to retrieve results.

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% for three parameters. The phrase 'per source' loosely connects to source_ids, but research_id and the optional questions array receive no explanation. The description does not compensate for the complete lack of schema-level parameter documentation.

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 states a specific action (generate evidence cards per source), its scope (one session per source, source-only basis), and the immediate return (task number). It distinguishes itself from general query tools through the per-source evidence-card framing, though it does not explicitly name a sibling alternative.

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 implied by the per-source evidence-card purpose, but the description never states when to choose this tool over siblings like dossier_query or dossier_compare, nor does it mention prerequisites or exclusions. An agent can infer intent but gets no explicit routing guidance.

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