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

Annotations already declare destructiveHint=true, so the description does not need to argue that this mutates state. It still adds real value by disclosing the human-in-the-loop consent requirement, which annotations cannot express. It stops short of stating that the replacement is irreversible or what happens if backup is left at its default false, which would complete the picture.

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 short sentences: the action first, the safety gate second. Nothing is padded and no sentence restates the tool name or annotations.

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 destructive, two-parameter mutation tool, the description covers the action, the upstream dependency, and the consent gate, with annotations handling the destruction signal. A note on irreversibility or on the consequence of the default backup=false would make it fully self-sufficient.

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%, with backup's default false and backup directory documented inline and plan_id tied to prepare_compression's return value. The description only echoes the plan_id provenance already stated in the schema, so the baseline 3 applies.

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 ('用 prepare_compression 的结果替换原图' — replace the original image with the prepare_compression result), which is unambiguous and clearly distinct from prepare_compression (plans) and cancel_compression (aborts). The downstream artifact of the sibling tool is named directly, so the agent can place this in the workflow without opening any 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?

Gives an explicit gating precondition rather than a vague hint: call only after the user has seen the preview table and explicitly consented. This is effectively both a when-to-use and a when-not-to-use rule, and it ties the tool to the prepare_compression workflow, leaving no doubt about sequencing among the siblings.

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

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

With no annotations provided, the description carries the full burden and does disclose real side effects: temporary files are removed and the original image is explicitly left untouched, which answers the main safety question for a cancel tool. It omits failure behavior (e.g. invalid or already-consumed plan_id) and any permission requirements.

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 sentence, front-loaded with the primary action, with the clarifying guarantee (original unaffected) placed last. Every clause earns its place.

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 single-parameter, no-output-schema cleanup tool the description covers purpose, side effects, and safety. It is only short of explaining where plan_id comes from and what happens on an invalid or expired plan.

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 one parameter at 0% schema description coverage, so plan_id is undocumented in the schema. The description implies provenance (it comes from prepare_compression) but never states that plan_id is that identifier, nor its format, so it only partially compensates for the coverage gap.

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 specific action pair — discarding the prepare_compression result and cleaning temporary files — so the agent immediately understands this is the abort path of a three-step workflow. It differentiates itself from prepare_compression by naming it, but never names apply_compression, the sibling it actually competes with when a prepared plan is outstanding.

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?

By stating that it discards the output of prepare_compression, the description anchors usage to a clear precondition: you have a prepared plan you no longer want. No explicit when-not or alternative (apply_compression) is offered, so the agent must infer the fork from the sibling list.

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

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

readOnlyHint=true is already declared, but the description adds real behavior the annotation cannot: output lands in a temp directory, the original files are untouched, and the call yields a plan_id plus a preview table. It does not cover failure modes or how long the plan_id remains valid, so not a full 5.

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?

Three tight sentences: capability and safety first, return values next, mandatory workflow constraint last. No repetition of the title or schema, and nothing 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 two-phase prepare/apply workflow with no output schema, the description supplies the return contract (plan_id + preview table) and the human-approval gate, which is what an agent most needs. Minor gaps remain around plan expiry or preview-table scale limits.

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% and the schema already documents paths, effort, min_score, and recursive in detail (including the SSIMULACRA2 threshold and enum meanings). The description adds no parameter-level information, so the baseline 3 applies.

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+resource ('视觉无损压缩图片') plus supported formats and output location (临时目录, 不修改原图). It also names the sibling it hands off to (apply_compression), so an agent can distinguish it from apply_compression and cancel_compression without opening a 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 sequencing rules: the preview table must be shown to the user in full, and apply_compression may only be called after the user's explicit consent. That is a when-to-use and when-not-to-use condition paired with the named alternative.

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