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

Goes well past the annotations (readOnlyHint/idempotentHint/non-destructive) by disclosing that pixels are not re-encoded, exactly which metadata classes are stripped versus kept (picture, color profile, orientation, IPTC digital source type), the 409 refusal case for C2PA signatures, and that failed calls are never charged. This is the kind of context an agent needs to predict cost and error behavior.

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 action and format list, then the refusal case, then limits and pricing — a sensible order. Minor waste in the redundant 'MCP tool: `clean_metadata`' and the standalone price sentence, but nothing that obscures the operative facts.

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?

With no output schema, the description still explains what comes back (cleaned file plus a removed/kept manifest) and covers the main edge cases: size routing, C2PA refusal, and billing on failure. An agent could call this correctly without opening anything else.

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% and there is a single documented parameter, so the baseline applies. The description adds an inline size threshold ('up to 1 MiB inline'), but that figure sits awkwardly against the schema's stated 4 MiB maximum for file_base64, creating an ambiguity rather than resolving one.

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 and resource ('Removes EXIF (GPS, device, timestamps), XMP, IPTC and text metadata from a JPEG, PNG or WebP and returns the cleaned file') plus the output shape. The removal-and-return framing separates it cleanly from a scan-style sibling such as scan_metadata without needing to name it.

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 concrete routing guidance: files up to 1 MiB go inline while larger files must use the upload job routes, and C2PA-bearing files are refused with 409 rather than cleaned. It lacks an explicit 'use scan_metadata instead if you only want to inspect' statement, so alternatives are implied rather than enumerated.

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