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

Annotations declare a non-read-only, non-destructive, non-idempotent, non-open-world tool, and the description adds genuinely useful behavioral context: results are stored for 24 hours, the response carries a storage_id enabling chained calls, and no API key or account is required. It does not clarify that 'strip' discards EXIF/XMP/IPTC irreversibly or specify payload size limits beyond the schema, but it goes well beyond 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?

A single dense paragraph, front-loaded with the resource and then a parenthetical parameter-to-operation map, followed by input sourcing and storage/chaining notes. Every sentence carries information, though the long parenthetical enumeration is packed tightly enough to be slightly hard to scan.

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 13-parameter, no-output-schema tool, the description covers input sourcing, format constraints per operation, the 24-hour result retention contract, and chaining via storage_id. Return-value details for metadata/colors/favicon are only implied, which is a minor gap given no output schema exists.

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 schema description coverage at only 23% across 13 parameters, the description compensates substantially by naming each parameter inline and binding it to an operation (format, quality, lossless, width, height, fit contain/cover, upscale, crop fit/trim/center, name, count, metadata, strip). It omits value ranges that the schema actually supplies (quality 40-95, count 2-16), so it is strong but not complete.

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 names a concrete resource (images in JPEG/PNG/WebP/HEIC/GIF) and enumerates the exact operations it performs: convert, compress, resize, metadata, strip, colors, favicon. An agent can tell what this tool does without opening the schema, and no sibling tool overlaps with image processing.

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?

It maps each operation to its relevant inputs (e.g. 'HEIC for convert and resize', 'GIF for metadata and strip') and routes the agent to the alternative input path ('store it with REST POST /services/v1/storage first and pass storage_id'). It lacks explicit when-not-to-use guidance, but the operation-to-format mapping is clear practical context.

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