knowledge_search

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

Annotations already cover readOnly, idempotent, non-destructive, and closed-world properties. The description adds modest value with 'Search is local and bounded', but says nothing about result format, ranking, or what pagination behavior to expect beyond what the schema implies.

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?

Two short, front-loaded paragraphs with no filler; the core action leads. The second paragraph is somewhat oblique, but the overall shape is tight.

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?

An output schema exists, so return values need not be described. However, with four undocumented parameters and no routing guidance against three similarly named knowledge_* siblings, the description leaves meaningful gaps for correct invocation.

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 description coverage is 0% across 4 parameters, so the description carries full burden. It never explains what 'kind' filters, and gives only incidental hints about query/limit/offset. The 'read hits by ID' phrasing further muddies parameter intent rather than clarifying it.

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+resource: search across 'manual, API, option, source, guide or capability documents'. That is clear and distinguishable from most siblings, though the appended clause 'read hits by ID' overlaps with the sibling knowledge_read and blurs which tool actually retrieves a hit.

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?

It gives context ('Search is local and bounded') and a caution about documented upstream functions not being executable tools, but never states when to use this versus knowledge_read, knowledge_catalog, or knowledge_status. Usage is implied rather than specified.

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