knowledge_search

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

Annotations already mark the operation read-only and non-destructive, but the description adds meaningful behavior: returns empty groups rather than padding with off-topic content, returns closest matches rather than a full index, and includes a system_instruction in each response. No contradiction exists.

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?

The description is longer than typical, but each sentence contributes meaning: core purpose, facet semantics, exclusions, behavioral guarantees, and response instructions. It is front-loaded with the main purpose before optional details, and no unnecessary repetition detracts from the value.

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?

Given the tool's five parameters, multiple sibling tools, and rich output schema, the description covers the full context needed for correct invocation: what it searches, what facets mean, what it deliberately does not search, and how results behave. The agent is well-equipped to select and call this tool.

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%, so the baseline is 3. The description goes beyond schema by explaining when each facet should be supplied and what it returns, e.g., company returns employer profile pages and job_title/location return job-listing landing pages.

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?

The description opens with a specific verb and resource: 'Searches FoundRole's published content by semantic similarity.' It clearly distinguishes from siblings by explicitly noting that knowledge_topics covers topic coverage and jobs_search covers live roles.

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 when-to-use guidance, such as 'a company mentioned only in passing does not need the company facet' and names alternatives for topic coverage and live job listings. This prevents the agent from misusing the tool for out-of-scope queries.

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