Say something

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

Annotations already declare readOnly=false, idempotent=false, destructive=false, openWorld=false, so the safety profile is mostly structured. The description adds genuinely new behavior: the buffer is live and ephemeral, lines expire (~20 s default) and are replaced, and the destination is the TUI at femboy://speech/live. Missing only what happens on failure or how the call acknowledgement looks.

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?

Two sentences, front-loaded with the action and its effect, then the expiry caveat. No filler and nothing repeated from the schema.

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 and full parameter coverage, the description covers the essentials: what gets written, where it goes, and that it is transient. It falls slightly short on what a successful call returns and whether concurrent lines overwrite each other beyond the ttl note.

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 description coverage is 100%, so kind, text, and ttl_ms are already documented with enum values and bounds; baseline 3 applies. The description adds the default expiry (~20 s) that the schema leaves unstated, which is a modest but real contribution.

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 names a specific verb-plus-resource ('push a line into the live speech buffer') and explains the downstream effect (TUI animates mouth and thought bubble). That is concrete enough to separate it from every sibling, none of which touch the speech buffer.

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 by the mechanism (speak a short line into the TUI), but there is no explicit statement of when to reach for this versus femboy_write_diary_entry or femboy_headpat, and no when-not-to-use condition. An agent can infer intent but must reason about the choice.

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