send

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

No annotations are provided, so the description carries the full behavioral burden. It discloses one important trait — a chat does not start work by itself — but says nothing about delivery guarantees, whether sending is idempotent, how `dedupe_key` affects retries, error semantics, or what happens on success. For a side-effecting send tool with zero annotation coverage and no schema descriptions, this is a substantial gap.

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 text is a single compact fragment with no filler, so there is no verbosity to trim. However, it is undersized for a five-parameter tool rather than genuinely concise, and the key behavioral nuance is tacked on after a semicolon rather than front-loaded.

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?

The presence of an output schema means return values need not be described, which helps slightly. But with no annotations and 0% parameter description coverage across five params, the definition leaves the agent without enough context to call `send` confidently regarding reply threading, dedupe behavior, or the chat/task choice.

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 0% for 5 parameters. The description loosely maps to `to` ('Addressed'), `text`, and `kind` (chat vs task), but leaves `reply_to` and `dedupe_key` completely unexplained, and never lists the valid values for `kind`. It does not compensate for the coverage gap.

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 the resource (an addressed chat message or durable task) but never states the verb in plain terms and reads as a sentence fragment, so the agent leans on the name 'send' to infer the action. It also does not differentiate itself from the plausible sibling 'say', which likely overlaps with the chat case. The distinction that a `chat` starts no work is useful but is behavioral, not identificational.

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?

There is no explicit when-to-use guidance, no statement of prerequisites, and no routing to alternatives among the many siblings (say, ack, accept, claim). The only implicit signal is that choosing `kind` selects chat vs task behavior, which the agent must reverse-engineer. No exclusions are stated.

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