thumbmoves_cached_thumbnail

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

Annotations already establish readOnly and closed-world behavior, but the description adds a non-obvious guarantee beyond them: a cache miss will not trigger a decode of the source file, so the call is cheap and side-effect free. It does not say whether a miss returns an error, null, or an empty result, leaving one meaningful behavioral gap.

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 semicolon-joined sentence with zero filler; the resource and the miss-behavior guarantee are both front-loaded. Every clause carries information an agent needs.

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?

An output schema exists, so return values and the miss shape need not be described, and the read-only nature is annotation-supported. However, with four nested parameters at 0% coverage and a nested argument wrapper, the description should say more about how quality, max_size, and output_format affect the read.

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 0% across four nested properties (path, quality, max_size, output_format), and the description only clarifies that the path is a "workspace file." It adds nothing about quality range, max_size pair semantics, output_format defaults, or whether these are honored on a cache hit, so the parameters remain undocumented in both places.

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?

"Read an existing OS thumbnail for one workspace file" gives a specific verb (read) and resource (OS thumbnail, singular workspace file), which is clearly distinct from generation/upscale siblings like rastermoves_upscale. It stops short of naming an alternative for the cache-miss path, so it is clear but not sibling-differentiating at the highest level.

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?

The phrase "a miss never decodes the source" implies the intended use case (cheap cache-only lookup) and implies an agent must fall back elsewhere on a miss, but no alternative tool or explicit when-not-to-use condition is named. Usage is inferable rather than stated.

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