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

With no annotations, the description carries the full burden and does so: it discloses default activation, patch-merge semantics on slug collision (kind/name preserved), refusal behavior for conflicting kinds, and the pending_review + review_id outcome under the review policy. Mutability and side-effect consequences are clearly surfaced.

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 core action, then merge semantics, then the review-policy branch. No filler; each clause conveys a distinct behavioral fact.

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 explained, and the description adds the policy-dependent outcomes an agent needs to interpret the call. Nothing essential for correct invocation is missing.

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 all five parameters are already documented; the description only adds the notion of slug derivation from name and the retention of kind/name on merge. Baseline 3 is appropriate since the schema does the heavy lifting.

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 ('Propose a typed ontology entity') and immediately scopes it ('active immediately by default'), distinguishing it from siblings such as memory_ontology_rekind_entity, which is named explicitly for the kind-change case.

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?

Explicitly covers when-not: attempting a different kind on an existing slug is refused and the agent must use memory_ontology_rekind_entity (with an org-admin note). It also routes the agent to the review flow when the entity_proposals policy is 'review', giving both the condition and the resulting status.

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