list_knowledge_gaps

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

Annotations already declare readOnlyHint/idempotentHint, but the description goes further by naming the remediation paths and the portal action, which is real operational context an agent can't infer from structured fields. It also enumerates the payload fields the detector attaches, useful given there is no output schema. It stops short of describing ordering or how to page beyond the schema's starting_after hint.

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 sentences, front-loaded with the identity of the resource, then payload shape, then default scope, then what to do instead of writing. No filler and no repetition of the tool name as a purpose statement.

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 six-parameter, zero-required, read-only listing tool with full schema coverage and no output schema, the description supplies the two things the schema can't: the meaning of a 'gap' and the field set returned. The gap is filter semantics for since/signal_type, which are only defined as terse schema strings.

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 the schema already documents limit, since, status, channel, signal_type and starting_after; the description only restates the status default and the 'all' escape hatch. It adds nothing about since (last_seen_at windowing) or the signal_type meanings (no_knowledge vs weak_match vs escalation), which are the least self-explanatory filters. Baseline 3 applies when the schema carries the load.

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 first sentence gives a specific verb+resource ('List knowledge gaps') and the second defines what a gap actually is ('Questions the AI could not answer well, flagged by the gap detector'), which no sibling tool covers. The five field names (customer message, AI reply, canonical question, suggested answer, target) further pin down the record type, so an agent can distinguish this from list_faqs or get_knowledge_usage without opening a schema.

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?

'Open gaps by default; status=all for everything' states the default scope and the override, and the closing clause tells the agent what to do instead of trying to mutate via this tool (create an FAQ, edit identity.instructions, or dismiss in the portal). What's missing is any explicit contrast with the neighbouring knowledge tools (list_faqs, get_knowledge_usage, list_documents) for the 'should I look here or there' decision.

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