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

Annotations already mark readOnly/idempotent/non-destructive; description adds valuable context: exactly which sources are searched, that results include slugs and snippets, and that the current conversation is excluded. It doesn't cover performance or result ordering, but those are minor for a search tool.

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?

Four sentences, each carrying distinct information: scope, usage triggers, return type, and exclusions. It is dense but efficiently structured; could be slightly more concise but each clause earns its place.

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 search tool with no output schema and full parameter documentation, the description covers scope, return content, exclusions, and proper alternative routing. It doesn't explain sorting or limit behavior beyond schema, but the overall picture is complete enough for an agent to invoke correctly.

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 already documents all three parameters with 100% coverage, so description needn't repeat. It does reinforce that query is the 'most specific keywords' and that companyId is required, matching schema. No additional semantic value beyond schema.

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?

Description states the specific verb 'Search' and enumerates the exact resource types it covers: FO Desk advisor chats, unbound chats the user is in, and Knowledge sitting captures. It also explicitly marks exclusions (grok buffers, current conversation), which clearly distinguishes it from similar search/list tools.

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?

Provides explicit user-phrase triggers ('remember when we talked about...', 'find that sitting') and names the alternative path for unsaved buffers ('capture those with save_knowledge'). Tells the agent when NOT to use it (current conversation, unsaved buffers).

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