speak

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

With no annotations to carry safety or behavioral signals, the description does most of the work itself. It discloses that the tool should not be used to read code or long text, that it should be called even when a conclusion is typed, and that spoken output must be short English (≤80 characters). It does not explain interrupt or priority behavior, but the core behavior is well covered.

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 purpose and usage, and each instruction serves a distinct function. The final 'Do not force Chinese' clause is somewhat redundant after the 'system UI language (en)' note, but it is a cheap and useful reminder.

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 simple output tool, the description covers required inputs, category mapping, output style, language, and call timing. The main gap is the undocumented 'priority' and 'interrupt' parameters, but these are optional and defaulted, so the description remains largely sufficient.

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. It does add meaning for 'text' (short, English, ≤80 characters) and 'category' (progress, errors, conclusions, decisions), corresponding to the enum values. However, 'priority' and 'interrupt' are never explained, leaving their semantics to names and defaults alone.

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 opens with a clear verb-plus-resource statement ('Speak a short status line for the user') and then enumerates the exact event types it is for: progress, task conclusions, errors/blocks, and decisions. This makes the tool's role obvious and distinguishes it from the sibling tool 'stop'.

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 explicitly states when to call it ('Use for real progress, task conclusions, errors/blocks, and when the user must decide or act') and when not to ('Do not read code or long text'). It also gives operational guidance about calling early instead of waiting for full-task completion.

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