knowmind_recall_memories

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

Annotations only cover the safety profile (readOnly/idempotent/non-destructive/closed-world); the description goes well beyond that, disclosing the retrieval pipeline, the return shape (top-k chunks with relevance score and source reference), the auth requirement ('Read scope suffices'), and a full decode of metadata.review_flags values (stale, unverified, superseded, drifted) and of kein_belastbarer_treffer. No contradictions with the annotations.

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?

Front-loaded with purpose and the sibling distinction, and every clause carries usable information. It loses a point because the review_flags enumeration is delivered as one very dense semicolon-chained sentence that is harder to parse than the rest of the text.

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?

With no output schema, the description carries the burden of explaining returns and does so: chunk count, relevance score, source reference, review_flags semantics, and the negative-signal flag. Auth scope and the time-scoped alternative are also covered, leaving nothing essential missing 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 100%, so all three parameters (including k's bounds and hops' no-op status) are already documented structurally; that sets the baseline at 3. The description adds only indirect hints ('top-k', hybrid recall) and no per-parameter syntax or format detail beyond the 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?

States a specific verb+resource ('Retrieve relevant knowledge') plus the scope ('over the tenant corpus') and the retrieval mechanism (hybrid BM25 + pgvector + knowledge graph). It explicitly names the sibling it is not (knowmind_recall_at_time) and the condition that distinguishes them, so an agent can route without opening either 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?

Gives an explicit trigger ('before answering anything that benefits from prior context - decisions, preferences, project state, people, deadlines, past conversations') and names the alternative tool plus the condition selecting it ('when you need what was valid at a past point in time'). It also tells the agent what to do when the result is empty of signal ('unless the hits clearly answer the question, say so').

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