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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false and closed-world, so safety is covered. The description goes further by disclosing the returned shape (title, access level, version, view count, URL) and the conditional HTML body payload, which annotations cannot express. It stops short of noting any rate limits or the response envelope, hence a 4 rather than 5.

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 compact clauses: the core fetch and its key identifier first, then the one optional behavior and its rationale. No filler, no repetition of the tool name, and the actionable guidance sits at the end where the agent reading left-to-right reaches it after learning what the call returns.

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?

There is no output schema, so the description correctly compensates by naming the metadata fields returned and flagging the opt-in HTML body. The in_workspace scope caveat lives only in the schema, but that schema text is thorough ('Nothing is stored; other sessions are not affected'), leaving no real gap for an agent.

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 baseline is 3; the description earns above baseline by explaining the intent behind include_html (read the current body so you can edit it) rather than just restating the schema's 'If true, include the latest version's HTML body'. It does not add anything further for in_workspace.

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 ('Fetch an artifact's metadata') and an explicit lookup key ('by id or slug'), then enumerates the returned fields. This clearly distinguishes it from artifacts_list (enumeration), artifacts_update (mutation) and artifacts_create.

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?

Routes the agent explicitly: set include_html=true when you intend to 'read-then-edit before calling artifacts.update', naming the downstream sibling. The trigger condition for the optional flag is spelled out rather than left to inference.

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