speak

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

With no annotations, the description carries the full burden and does well: it discloses the files written (voice.wav, voice.json with line times), the side effect of setting the project voice, caching behavior (only changed lines cost money), and the paid-operation guard that estimates first and refuses over budget. It stops short of stating what the call itself returns or how failures other than budget are surfaced.

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?

It is dense and front-loaded, leading with the verb and the payload shape before side effects and cost. The telegraphic abbreviation style ('gap_s', 'Paid:') trades a little readability for compactness but every clause carries information.

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 3-parameter generation tool with no output schema and no annotations, the description covers inputs, side effects, artifacts, caching, and cost gating. The remaining gap is what the invocation itself returns (e.g., file handles or line times inline) versus only the on-disk artifacts.

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 0%, so the description must compensate and it does: 'lines' is explained as string-or-object with text/pace/emotion, pace gets accepted values plus a 0.5-2 factor range with concrete examples, emotion gets a 20-character cap and multilingual examples, and gap_s is defined as inter-line silence. This turns an opaque anyOf schema into something callable.

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 verb 'Narrate' plus the concrete output ('voice/voice.wav and voice/voice.json') makes clear this synthesizes speech for a project. It is distinguishable from siblings like animate or draw by the audio-narration focus, though it never explicitly contrasts itself with them.

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 rather than stated: an agent can infer this is the text-to-speech step and that it 'sets the project's voice if unset'. There is no explicit when-to-use/when-not guidance or named alternative among the siblings, and the budget behavior is described as a property rather than a decision rule.

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