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

Goes well beyond the readOnly/openWorld/idempotent annotations: it discloses that nothing is sent by the tool, that the person sends the email themselves, what the response contains (help center section, support address, mailto link), the AI-disclosure line behavior, and a refusal rule for private keys or seed phrases. That refusal rule is behaviorally critical and appears nowhere in structured fields.

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 purpose and the when-to-use condition before the return-value and safety details. Dense but nearly every clause carries information; the middle sentence about help center/mailto is long but justified because there is no output 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?

No output schema exists, yet the description documents what is returned, what is not done (no send), how replies arrive, and the refusal edge case. For a 5-parameter escalation tool with readOnly annotations, 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?

With 100% schema coverage the baseline is 3; the description adds real meaning on top — subject is in the person's words and defaults to topic plus token ID, discloseAgent suppresses the AI-drafted line, and the mailto link carries the property page the other tools link. It mostly restates the schema for summary and topic, but the discloseAgent and subject interactions are explained in context.

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 resource (hand a question to Fabrica's support team) and explicitly positions itself as the escalation path when ask_fabrica fails. An agent can distinguish it from the knowledge-base sibling without opening either schema.

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 when-to-use triggers — documents don't answer it, or a person is needed — with concrete examples (stuck property add, document question, dispute). It names the alternative (ask_fabrica) and the condition that selects this tool over it.

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