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

Goes well beyond the destructiveHint/openWorldHint annotations: it pinpoints which branch is irreversible ('a send cannot be undone'), explains that passing text overrides the agent's draft rather than merely editing metadata, and discloses the non-obvious behavior that a 'confirm' card sends nothing and that its labels define the meaning of yes/no.

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?

Front-loads the core action and the two decisions before the safety caveat and the confirm-card edge case. Dense but nearly every clause carries unique instruction; the confirm-card sentence is long but earns its place as a distinct branch.

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 destructive, no-output-schema mutation, the description supplies the safety gate, the branch semantics, the override rule and the special-case card type. Nothing an agent needs to call it correctly is missing.

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 75% and already documents text, cardId and reason, so baseline is 3. The description adds real semantic value on the one undocumented element (decision values) and clarifies that text is an alternative to the agent's draft and reason is for agent learning, but it doesn't restate formats for the remaining parameters.

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 the specific verb (decide) and resource (a waiting card), then enumerates the two decisions and their effects ('send' sends on LinkedIn now, 'skip' drops it). An agent can distinguish this from list_cards, get_brief or talk, which are named as the sources of cardId.

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?

Explicitly gates invocation: 'Only call this after the user has seen the exact text and said what to do.' It also routes the two decisions and explains how 'send'/'skip' map onto a 'confirm'-kind card, so no ambiguity remains about when and with what value to call it.

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