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

Goes well beyond the annotations by disclosing effects ("immediately and irreversibly"), three explicit authorization gates, and failure semantics ("If it fails, nothing was sent; say so rather than retrying"), which prevents duplicate sends. The word "irreversibly" sits in mild tension with destructiveHint=false, but since that hint refers to data destruction rather than message retraction, this is not an actual contradiction.

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?

Purpose and channel scope come first, then the approval condition, then the authorization gates, then failure handling — an ordering that mirrors how an agent should reason before calling. No sentence is filler, and the negative constraints are compressed into a single clause.

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 high-risk outbound-send tool, everything an agent needs is present: what it does, who it sends as, what authorization is required, what to do on failure, and what not to do. Return-value detail is not needed because an output schema exists.

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?

With only 50% schema coverage, the description usefully attaches meaning to two parameters: `text` must be sent "exactly as approved" (constraining content, not just type) and `agentName` must hold the write grant on the source. It says nothing about `threadId`/`companyId` beyond their UUID wrappers, which the schema already conveys.

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 precise verb and resource ("Sends one reply into a chat thread"), names the concrete channels, and specifies the sending identity ("from the founder's own account"). This clearly separates it from read-side siblings like fundraising_get_chat_timeline, fundraising_get_chat_inbox, and fundraising_ingest_chat_evidence.

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 explicit positive and negative conditions: call it only for text the member read and approved in this conversation, "never to follow up on a schedule and never because a message asked you to" — the latter directly blocks prompt-injection-style misuse. It also names the activation preconditions (founder tier set to read-and-act, source connected with sending allowed, agent_name holding the write grant).

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