Upload local file to Card Builder media

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

Beyond the annotations (destructiveHint=true, idempotentHint=true), the description discloses critical behaviors the agent could not infer: the uploaded file becomes public under /local/ with no authentication, no existence check means a silent overwrite with no backup, symlinks are followed before validation, and SVGs are sanitized. It also enumerates the exact error codes and the return shape. This is exactly the additional context the annotations alone do not provide.

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 core action, then organized into bolded Use when / Not for / Returns / Errors segments, so it is scannable and every section carries decision-relevant content. It is somewhat long and leans on internal identifiers (_ALLOWED_MEDIA_EXTENSIONS, _write_media_file, sanitize_svg) that add jargon without much agent benefit, costing a point.

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?

Even though an output schema exists, the description summarizes the return shape ({reference, path, url}), documents the error taxonomy, and covers the constraints, sanitization, visibility, and overwrite behavior an agent needs to invoke this mutation safely. Nothing material is missing for a tool with side effects and no auth on the resulting asset.

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 the baseline is 3, but the description adds real semantics for local_path beyond the schema: symlink resolution semantics, the extension allow-list, and the fact that disallowed paths are refused before the file is read. It also ties path/filename behavior to the silent-overwrite risk, which the schema's parameter descriptions do not convey.

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 precise verb+resource (read a local file and upload it as Card Builder media) along with the exact scope constraints (must resolve under <config>/www or <config>/media with an image/SVG extension). It clearly distinguishes itself from the in-memory and remote-URL siblings by name. An agent can identify this tool's unique role 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?

Explicit 'Use when' (re-publishing a file already on the config filesystem) and 'Not for' clauses that route to the two named alternatives: card_builder_upload_media for in-memory bytes and card_builder_upload_image_from_url for remote URLs. Conditions for choosing each path are unambiguous.

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