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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is low, but the description adds substantive context the annotations cannot: results are AI-drafted from customer conversations and the text is untrusted content. That is a meaningful prompt-injection warning for an agent that will subsequently read this data.

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?

Three tight sentences, front-loaded with the corpus disambiguation before the action. The parenthetical is the only extra syntax and it earns its place by preventing a wrong-corpus call.

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?

Output schema exists so return shape need not be explained, and annotations cover the safety profile. The description still supplies the three things structure cannot: corpus scope, the review follow-up, and the untrusted-content caveat.

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% and both parameters (limit, status) carry their own descriptions and defaults, so the schema does the heavy lifting. The description only hints at the default by saying suggestions 'await a decision,' without adding syntax or semantics beyond what is already documented.

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 (list knowledge suggestions) plus the defining scope: suggestions the AI assistant drafted from conversations and that await a decision. It also pre-empts the most likely confusion by naming the sibling kb_list_articles / search_knowledge territory as a different corpus.

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 routes two alternatives: use search_knowledge for Spun's product documentation, and use kb_review_suggestion to act on a suggestion. It also implies the natural next step after listing, so the agent knows both the wrong path and the follow-up path.

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