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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the agent knows this is a bounded local write. The description usefully adds that the record becomes visible to the owner's and teammates' agents, but it does not address non-idempotency: nothing warns that saving the same content twice creates a duplicate rather than updating it, which is the main misuse risk here.

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 sentences with no filler, front-loading the action and purpose before the usage trigger. The reference to the sibling search tool is placed where it supports the agent's next step.

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 simple create tool with full schema coverage, no output schema and annotations covering the safety profile, the description covers purpose, visibility implication and usage trigger. The remaining gap is what happens on repeated saves and whether an identifier comes back, which matters for follow-up operations.

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 explains title, body, kind, tags, source and the team/private visibility semantics. The description adds no field-level guidance, such as what makes a good searchable title or when to prefer visibility=private. With the schema fully documented, baseline 3 is appropriate.

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 description states a specific verb and resource: save a finding, decision or result to shared knowledge. It also names the retrieval counterpart, search_knowledge, which pins down what the record is for. It does not distinguish itself from update_knowledge or retire_knowledge, so an agent that already has an entry cannot tell from this text whether to save again or update.

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?

The trigger is explicit and behavioral: whenever you learn something others will need. It also points at search_knowledge as the read-side alternative, which clarifies the write/read split. There is no when-not guidance for the edit/retire siblings, so the coverage of alternatives is incomplete rather than wrong.

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