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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is known; the description adds genuinely new behavior — a strict whitelist with all-or-nothing refusal, null/[] clearing semantics for faqs, and null rejection for title/slug/content. It does not cover permissions, error behavior for missing articles, or whether the write is atomic across multiple keys.

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 the scope constraint and refusal rule, followed by the whitelist and the null rules — no filler sentences. The dense comma-separated key list and line breaks make it slightly harder to scan than a bulleted form, but every sentence earns its place.

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 mutation tool with annotations but no output schema and an untyped nested parameter, the description supplies the critical information an agent needs: allowed keys, refusal semantics, null handling, and identifier choice. Remaining omissions (identifier exclusivity, error response shape) are secondary but real for a destructive write.

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 0% and the required `updates` object is untyped with additionalProperties=true, so the description carries the full burden — and it does: it enumerates the exact allowed keys, specifies the faqs element shape {summary, text}, and defines null/[] semantics. The gap is that it never states whether article_id and article_uuid are mutually exclusive, whether one is required, or which wins if both are passed.

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 and resource ('Update only the allowed keys of a seliee_article') and scopes it to a whitelist of fields, which is far more precise than the tautological title. It does not name the closely related sibling edit_article, so the boundary against alternatives is left implicit.

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 clear operating context: only whitelisted keys are accepted, anything else is refused and nothing is written, and the record is located by article_id or article_uuid. It stops short of naming an alternative tool for editing non-whitelisted fields, so routing against edit_article is inferred rather than stated.

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