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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true; the description usefully adds the authorization requirements and the optimistic-concurrency precondition ('at the expected revision'), plus clarifies two things it does not do. It omits what happens on a revision mismatch, what existing guidance is overwritten, and says nothing about retry safety despite the schema offering an idempotency_key.

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 tight sentences, front-loaded with the core action and followed by permissions and negative scope; no filler. It loses a point only because it largely restates the title verbatim rather than adding new information.

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?

This is a destructive, non-idempotent write with 8 required parameters, no output schema, and near-zero schema documentation — exactly the case where the description should explain field meanings and mismatch behavior. It does not, leaving an agent unable to construct a correct call from prose alone.

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 only 10% for 10 parameters, so the description must carry the load and it does not. It maps loosely to 'case' (provenance), 'text' (operator text) and 'revision', but leaves the critical distinction between 'text' and 'knowledge' undefined, and says nothing about 'source' (correction vs reply), 'environment', 'replaces', or 'idempotency_key'.

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 ('Save') and a specific resource ('the exact reviewed reusable fact in shared company core guidance') plus provenance and revision preconditions. It implicitly contrasts with the preparation step and with reply-sending flows, but never names the sibling tools (e.g. summer_cases_teaching_prepare, summer_knowledge_create) it must be distinguished from.

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 real preconditions ('requires cases.read and current company and Ops admin rights') and two exclusions ('does not send the reply or restart an agent'). However, it never says when to pick this over the many other write tools in the family (knowledge_create/edit, guides_save, teaching_prepare), so usage is only implied.

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