Search knowledge pages

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds two useful behavioral notes — results are historical ("Hindsight only") and claims should be checked against the code, implying possible staleness — but says nothing about result volume, ranking, or what a page hit contains.

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 sentences, front-loaded with the resource and scope, then the usage triggers. "Hindsight only" is tersely phrased and slightly ambiguous, but nothing is wasted.

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 read-only search with full schema coverage and no output schema, the description covers purpose and timing adequately. It leaves open what a page hit is and when to follow up with memory_pages_read, which is the main remaining gap.

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 100%, so query, bank and limit are already documented in the schema including the default bank and default limit of 5. The description adds no meaning beyond that, which is the expected baseline when the schema does the work.

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 ("Search knowledge pages") and narrows the content to "past decisions and conventions", which separates it from the general memory_search sibling. It stops short of explicitly distinguishing itself from memory_pages_list or memory_pages_read, so an agent still has to infer the split.

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 concrete triggering situations (before fixing a bug, changing a test, building something) plus a verification instruction, which is clear usage context. No exclusion or alternative is named, so the agent isn't told when to prefer memory_search or memory_pages_read instead.

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