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

Annotations already declare readOnlyHint=true, so safety is covered. The description adds one genuinely useful behavioral fact — that the call depends on an active practice run and is a recovery aid — but says nothing about what happens when no run is active or what form the response takes.

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?

One short sentence, front-loaded with the action and resource, with the recovery example placed after the main clause. No redundant or filler wording.

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 one-parameter read tool with no output schema and only a readOnly annotation, the description covers the trigger but not the outcome. An agent cannot tell from this text whether the return value is an image, a drawing state object, or a status, which is the main thing lacking for a tool whose whole job is retrieval.

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?

There is a single parameter with 100% schema description coverage, so the schema fully documents the API key. The description adds no meaning beyond that and does not reinforce the key requirement, which is acceptable at this coverage level but yields baseline rather than added value.

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 ('Show the drawing you are on') and scopes it to 'your active practice run', which ties it to the sibling start_practice session. It is clear enough to distinguish from create_key or guess, but the mismatch between the name get_image and the term 'drawing', plus silence on how it differs from get_result, keeps it below a 5.

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?

Supplies one concrete use case ('for example after a lost connection'), which gives an agent a real trigger for calling it. However, it never says when not to call it or how it relates to the sibling get_result, so the agent must infer the boundary between the two retrieval tools.

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