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

With no annotations, the description carries the full behavioral burden. It discloses grouping behavior, synonym-awareness, and the effect of include, which is useful. Yet it doesn't explicitly state the operation is read-only, nor describe the return structure beyond 'full summary', pagination, or error handling. These gaps mean the description only partially covers behavioral context.

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 description is a single, dense sentence that packs key usage information with no fluff. It front-loads the core behavior (grouped by type) then details options, making it efficient and easy to scan. Every clause adds value, from the summary mention to the synonym-aware nuance.

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?

Without an output schema, the description should hint at the return format. It mentions 'by_type_counts is the full summary' and 'inline the bodies', which gives some structure, but it lacks details on pagination, limits, or how to interpret the grouped response. For a tool with four parameters and no output schema, a bit more context on the response shape would improve completeness.

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 50%, so the description compensates for undocumented parameters. It explains `type` (scoping) and `include` (inlining content) with specific examples, adding value beyond the schema. The `context` parameter is already described in the schema, and `aid`'s purpose is inferable. This is a solid contribution to parameter understanding.

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 clearly states the tool returns a specific API's artifacts grouped by type, with a key summary ('by_type_counts'). It identifies the resource (one API, via `aid`) and the primary action (get artifacts). While it doesn't explicitly differentiate from siblings like get_provider_artifacts or find_artifacts, the scope is specific enough to infer its purpose.

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 description gives practical parameter usage (e.g., 'pass type to scope', 'include=["content"] to inline bodies'), which helps an agent use the tool. However, it provides no guidance on when to choose this tool over siblings, nor any exclusions or alternatives. The synonym-aware note is about parameter behavior, not tool selection, so the usage context is incomplete.

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