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

Annotations are minimal (readOnlyHint=false, destructiveHint=false), so the description bears the burden of behavioral disclosure. It states the filter operation but never says whether the original is left intact, whether a new processed file is produced, or any side effects of processing. The one useful behavioral fact — HEIC/HEIF output comes back as JPG — is buried in the schema, not the description. There is no contradiction with the annotations.

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?

Two sentences with the purpose front-loaded and no rambling. However, the 'Photo Editor —' prefix redundantly echoes the title, and the '[category: photo]' tag is empty filler that duplicates what the tool name and sibling set already convey. The filter list is useful but duplicates the schema enum.

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 simple 2-parameter tool with 100% schema coverage, the description plus schema covers the essentials (input formats, filter options, size cap, output-format exception). The weakness is thin behavioral context — what happens to the source file and what output is returned — but for a straightforward single-filter tool this is an adequate, not excellent, level of completeness.

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 100%: the file param documents accepted formats, the 25MB size limit, and the output-format rule, while the filter param has a descriptive enum. The description only re-lists the enum values, adding marginal meaning beyond what the schema already provides. Baseline 3 is appropriate since the schema does the heavy lifting.

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?

The description states a specific verb+resource ('Apply a single named filter to an image') and enumerates the six filter options, which clearly separates it from the analyze_* and convert_* families. However, it does not explicitly distinguish itself from the many close photo_* siblings like photo_color_adjuster or photo_noise_reducer — the filter list helps, but the routing is implicit.

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?

No guidance exists on when to use this tool versus its close siblings. With roughly 30 photo_* tools in the sibling list — several of which (photo_color_adjuster, photo_noise_reducer, photo_face_blur) overlap with what 'filter' could mean — an agent gets no explicit when-or-when-not signal. The 'single named filter' constraint is the only implicit selector.

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