Send a message

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

With no annotations, the description carries the full load and does so well: it discloses the idle debounce (~3 s), that blocked programs are refused, the force caveat, and that wait=true waits for and reports the resulting turn. It is silent on what a wait=false call returns, which matters since there is no output schema.

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?

Four short sentences, front-loaded with the core action, then constraints, then the anti-pattern warning. No sentence is redundant and nothing is repeated from the schema verbatim.

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 mutation tool with six parameters and no annotations or output schema, the description covers the risky behaviors (debounce, blocked refusal, force semantics, wait reporting) and adds a recovery instruction. Gaps remain around the return value on wait=false and what happens when the 'if' precondition fails.

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 100%, so baseline is 3; the description still adds meaning by linking force to the blocked-program refusal and explaining that wait=true returns how the turn ended, plus the idle timing that underpins the 'if' enum. It does not clarify the conditional behavior when 'if' is not satisfied.

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?

States a specific verb and mechanism: paste text into a terminal and press Enter. That mechanism-level phrasing distinguishes it implicitly from sibling writers like herdr_put and herdr_keys without the agent needing to open their schemas.

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?

Gives concrete context for conditional behavior (only after ~3 s of no typing), the force escape hatch, and when to use wait=true. The closing instruction 'do not resend after an unclear result: read first' routes the agent to a read-first workflow, though it does not name the sibling tool explicitly.

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