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

Beyond the annotations it discloses the retry semantics ('Identical retries reuse the asset'), the non-publishing guarantee ('upload publishes nothing'), the accepted formats and hard size ceiling (PNG/JPEG/WebP up to 8,000,000 bytes), and the return value (asset ID plus private preview). It also states a consent/authorization precondition ('After explicit user instruction', 'provide documented rights') that annotations do not express.

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 and constraint, and each sentence carries non-redundant information. The conditional sibling-workflow sentence is long and dense, and the mixed-language title ('Privat hochladen') against an English description adds minor friction, but nothing is padding.

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 mutation tool with six parameters, nested rights objects, and no output schema, the description covers purpose, preconditions, input sourcing, size limits, return value, and the downstream workflow. The remaining gap is the semantics of the nested rights object and of title/tags, which neither the schema nor the description explains.

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?

With 0% schema description coverage the description carries the burden and does real work for the risky parameters: imageFile must be the real attached file with host download_url and file_id, imageBase64 must be the exact original, and expectedRevision is sourced from list_social_images. It adds a critical semantic constraint ('never a fabricated URL or generated replacement'), but title, tags, and the six nested rights sub-fields (channels, subjects, expiresAt, consentEvidence) get only 'provide documented rights' with no guidance.

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 and resource with scope: 'store one original image privately in the existing tenant library', and immediately clarifies that 'upload publishes nothing'. An agent can distinguish this from list_social_images and from any publish workflow 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 preconditions ('After explicit user instruction'), an explicit dependency ('Read list_social_images for expectedRevision'), and an explicit branch on sibling availability: use prepare_business_profile_post/show_maps_approval with imageAssetId when exposed, otherwise keep the private asset and use an available post workflow. When-to-use and what-to-do-next are both covered.

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