Get a reference analysis

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

Annotations only establish readOnly/no-destructive; the description goes far beyond by disclosing the full state machine (queued, analyzing, succeeded, failed), which payload each terminal state carries (reference_profile in mode full vs data in mode data, plus warnings), the complete error code set (timed_out, analysis_failed, asset_gone, enqueue_failed), and billing behavior (credits_charged is the price on success, 0 on failure, free to call). This is exactly the kind of behavioral context the description should carry.

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?

Front-loaded with the core purpose, then structured by outcome (success/failure) with the cost note last. Every clause adds decision-relevant information; 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?

With no output schema, the description must explain return values, and it does so thoroughly: per-state payload shapes, error structure with enumerated codes, and the credits_charged semantics. An agent has enough to parse results and decide whether to keep polling.

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?

There is one required parameter with 0% schema description coverage, so the description carries the burden. It implies provenance (the analysis_id coming from analyze_reference) but never states the expected id format, whether a stale or foreign id is tolerated, or what happens with an unknown id — the pattern ^ref_[a-f0-9]{32}$ is only visible in the schema. Adequate but leaves a real gap for the sole input.

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?

Opens with a specific verb+resource ("Read an analysis started by analyze_reference") and immediately distinguishes it from the enqueue/start sibling, which is the only tool that creates these analyses. An agent can tell exactly what it gets back without opening a schema.

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 makes clear this is the read side of analyze_reference and that it must be called with the id from that call, implying the poll-until-terminal pattern through the enumerated queued/analyzing/succeeded/failed states. It stops short of stating polling cadence or explicitly excluding alternatives (e.g. re-calling analyze_reference or quote_analysis).

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