Upload attachment

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

Annotations already flag it as a non-read-only, non-destructive, open-world write, so the bar is lower; the description still adds real context: the authenticated Polarion user needs attachment write permission, sources are gated by environment allowlists, and dry_run previews name/size/SHA-256 before sending. It does not say whether re-uploading an identical file creates a duplicate, which matters given idempotentHint=false.

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 dense sentences, front-loaded with verb and targets, then source constraints, then permission and dry_run guidance. No filler, though the middle sentence packs several environment-variable conditions together and the closing sibling reference is slightly vague ('resource-specific attachment tools').

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-target, six-parameter write tool with no output schema, the description covers target scope, source channel, permission prerequisite, preview mode, and return shape. The single omission is the relationship to the sibling per-resource upload tools, which an agent would need to avoid picking the wrong tool.

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 100%, so baseline is 3; the description earns a point by stating the mutual-exclusion rule ('choose exactly one source') between `filePath` and `url`, a constraint not expressed as oneOf in the schema. It also clarifies that dry_run is for validation/preview rather than a separate mode.

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 plus the resource ('Uploads one file as a Polarion attachment') and enumerates all four target families (Work Item, Test Run, LiveDoc, Rich Page). It also states the return ('returns the attachment result'), so the tool is fully identifiable without opening the schema.

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 explicit context: 'Choose exactly one source' between local path (stdio + MCP_UPLOAD_ROOTS) and HTTPS URL (allowlisted host), plus when to use `dry_run`. The one gap is that it never disambiguates from the many sibling post*Attachments tools (postWorkItemAttachments, postPageAttachments, postTestRunAttachments, etc.) that appear to overlap heavily; it only routes away from itself for 'editing existing attachment metadata or content'.

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