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

Annotations only cover readOnly/destructive/openWorld, so the description carries real weight: it discloses billing (weekly coverage then purchased Credits), states 'This never launches an agent' (important among the agent_* siblings), and warns that sources/skills are untrusted reference data rather than permission. It does not disclose what the response looks like or whether the write is atomic, but the output schema covers returns.

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?

The creation action and space default are front-loaded, and each sentence carries distinct information (defaulting, billing, no-agent-launch, versioning, trust model). The sentence 'Updates and removal require the exact current version; skills share this knowledge authority' bundles two unrelated points, which slightly muddies readability.

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 nested, 8-parameter mutation tool with an output schema and useful annotations, the description covers the non-obvious operational facts well but leaves required inputs like idempotency_key and kind unexplained. An agent could call it, but would be guessing at several required field semantics.

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 0% across 8 parameters including 4 required ones, so the description must compensate and largely does not. It explains space_id's omission behavior and characterizes sources as untrusted reference data, but says nothing about idempotency_key, title, text, path, the 'kind' enum values, or the provenance/premise_versions structure.

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?

Opens with a specific verb+resource ('Create entries') and scopes it to one authorized private Space, defaulting to Personal. It implicitly distinguishes itself from private_knowledge_update/remove by noting that updates and removal need the exact current version, but it never names those siblings outright.

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 omission rule for space_id ('Personal when needed') gives usable context, and the note that updates/removal require a current version hints that this tool is for new entries only. There is no explicit when-to-use / when-not / alternative-tool routing against the many sibling knowledge and skill tools.

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