a11y-toolkit: Screen reader transcript

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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint=false), the description adds valuable behavior: it 'walks the accessibility tree linearly' and explains the output as 'announcement text with roles, names and states'. It also discloses the Playwright dependency, which is not present in structured data. No contradiction with annotations.

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 front-loaded with the core purpose ('what a blind user HEARS') and then provides distinctions and requirements. It is fairly concise, though the phrase 'the linearized reading experience, as prose an agent can READ' is slightly redundant with the earlier 'Walks the accessibility tree linearly and returns the announcement text with roles, names and states'.

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 compensates by describing the return value as announcement text with roles/names/states as prose. It includes prerequisite Playwright and differentiates from siblings. Missing edge cases or error behavior, but these are minor for a read-only transcription tool.

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?

The input schema has 100% coverage with each parameter (url, lang, timeout) already described. The description does not add additional parameter-level meaning, so the baseline of 3 is appropriate.

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 clearly states the tool's function: it walks the accessibility tree linearly and returns announcement text with roles, names, and states. It also differentiates from siblings by naming a11y_snapshot for structure and a11y_keyboard for keyboard traps, so an agent can distinguish it from other a11y tools.

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?

Explicit guidance is given: 'for structure use a11y_snapshot, for keyboard traps use a11y_keyboard' directly steers the agent to alternatives, and the 'Read-only' label indicates when to use this tool. The requirement 'Requires Playwright' also serves as a practical precondition.

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