Review a program draft

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

The readOnlyHint annotation already signals no mutation; the description reinforces this with 'saves nothing' and discloses the return shape {ok, violations, warnings}. It also reveals what the tool checks (weights, equipment, session length, weekly days, injury conflicts), going beyond the annotation without contradicting it.

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?

Three sentences carry the full story: what it is, when/how to call it, what it checks, what it returns, and that it persists nothing. Every sentence earns its place and the most decision-relevant info is front-loaded.

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?

For a complex nested-parameter tool with an output schema available, the description covers the essential workflow, return contract, and side-effect profile. The agent knows when to invoke it, what to pass, what to expect back, and what to do next — nothing critical is missing.

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?

With 0% schema description coverage, the description compensates by explaining that the single 'document' parameter should be the same WorkoutDocument the agent intends to import. This adds real semantic guidance beyond the raw schema, though it does not detail the document's internal subfields — the nested schema itself covers those.

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 verb ('review'), a specific resource ('DRAFT training program'), and a concrete server-side behavior (checklist). It differentiates this from import_document by framing it as a pre-import validation step, and from get_program by making clear it operates on a draft, not an existing program.

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 gives explicit when-to-use guidance: call it with the same WorkoutDocument intended for import, before presenting the draft to the user, and re-check after fixing violations. It does not explicitly list when-not-to-use scenarios or name alternatives, but the pre-import workflow is clear enough to route an agent correctly.

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