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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint=false), but the description adds non-obvious behavior the annotations cannot: results contain relative storage paths, signed preview links stay private widget data, and each folder is capped at its newest 100 files with truncation reported. That truncation cap is exactly the kind of limit an agent needs before assuming completeness of results. It does not describe pagination or how to retrieve files beyond the 100 cap.

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?

Three tight sentences with the resource enumeration front-loaded, followed by the read/write distinction, then the return-shape and truncation caveats. No filler. The 'Upload is an explicit widget action' clause is slightly oblique but earns its place by preempting a read/write confusion.

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?

An output schema exists, so return structure need not be explained, yet the description still adds useful return semantics (relative paths, private signed links) plus the 100-file-per-folder truncation rule. Combined with annotations covering safety and idempotency, an agent has enough to call this correctly. The only real gap is disambiguation from the many sibling list_* tools.

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%, so the description must compensate and it largely does not — projectId is never mentioned, though 'a project's screenshots' implies project scoping. The schema itself supplies the uuid format and pattern, which limits the damage. With a single required parameter, an agent can still call this correctly, so 3 rather than lower.

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 (Returns/List) and enumerates the resource precisely: screenshots, illustrations, icons, backgrounds, panoramas, recordings, music, clips and fonts, scoped to a project. An agent can tell this is the broad project asset library rather than a single-type list. It stops short of naming the overlapping siblings (list_screenshots, list_illustrations, list_fonts, list_asset_folders), so the boundary is inferred rather than declared.

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?

'Listing is read-only; Upload is an explicit widget action' clarifies the read/write split versus upload_asset, but only obliquely. There is no explicit statement of when to call this versus list_screenshots, list_illustrations, list_fonts or list_asset_folders, which are the real ambiguity for an agent given the large sibling set. Usage is implied by the enumerated asset types rather than guided.

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