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

Description adds important behavior beyond annotations: sequential processing, paid quota consumption, stop-on-first-failure, and reporting of completed files. This complements the readOnly=false annotation without contradicting it. Could still note API-key/auth requirements more explicitly, but the added context is strong.

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 dense sentence front-loads the core capability, then adds cost and failure behavior without filler. Every clause adds new information.

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?

With no output schema and zero parameter descriptions, the tool needs more context to be invoked correctly—especially since optional fields like api_key, model, quality, and response_format are unexplained. 'Reports completed files' is too vague about the return payload; missing parameter semantics make the definition incomplete.

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%, so description must carry parameter meaning. It only clarifies image_paths (up to 10 local images) and prompt ('one prompt'), while leaving size, model, api_key, quality, and response_format unaddressed. This is insufficient for 7 parameters.

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?

Description uses specific verb 'Edit' and resource 'local images' with a hard cap of 10, making the batch intent clear. It does distinguish from a single-image edit by quantity, but never names sibling tools like image_edit or image_multi_reference, so the differentiation is implied not explicit.

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 sentence tells the agent when to choose this tool over image_edit, image_generate, or image_multi_reference. The batch/10-image wording implies a multi-image use case, but there are no explicit exclusion criteria or alternative references.

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?

Annotations declare readOnlyHint=false, so mutation is already implied, but the description adds meaningful context beyond annotations: the reference image is uploaded and the operation consumes paid quota. This is useful cost and data-flow information that is not present in the structured metadata.

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?

The description is three short sentences with no filler. The action is front-loaded, and each sentence adds distinct information: the operation, the upload behavior, and the cost implication.

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 an 8-parameter tool with no output schema and no parameter descriptions, this description is far too sparse. It lacks any information about the editing prompt, return format, how the image is processed, or how parameters interact. An agent would struggle to call this tool correctly based solely on the description.

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%, and the description does not compensate. It only vaguely refers to a 'reference image', which maps loosely to image_path, but all other parameters (prompt, size, n, model, quality, response_format, api_key) remain completely unexplained. This is a severe gap for a tool with 8 parameters.

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 opens with a specific verb and resource: 'Edit one local PNG/JPEG/WebP through PdhAPI.' It clearly identifies the tool's core function and hints at single-image scope with 'one local', which loosely distinguishes it from batch and multi-reference siblings. However, it does not explicitly name or contrast any sibling tool.

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 is given for when to use image_edit versus image_generate, image_batch_edit, or image_multi_reference. The note about a reference image being uploaded implies editing an existing image, but there is no explicit selection rule or exclusion of alternatives.

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?

The description reveals that calls consume paid API quota, which signals non-idempotency and cost, and that output is local files and previews. It also warns against automatic retries after timeout, adding operational behavior beyond the annotations. No contradiction with 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?

The description is three concise sentences, each carrying distinct information: purpose, cost, output, and retry guidance. It is front-loaded with the primary action and has no wasted words.

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?

The description is incomplete for a 7-parameter tool with no output schema: it doesn't explain parameter meanings, response structure, or how to access the local files/previews. It covers cost and retry but misses critical invocation details.

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 0% schema description coverage, the description should compensate by explaining parameters, but it doesn't mention any of the 7 parameters. Names like n, response_format, and quality are left to the agent's guesses, so the description adds no semantic 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?

The description states a specific action (generate images) and resource (PdhAPI). The verb 'generate' distinguishes it from the sibling edit/batch tools, though it doesn't explicitly mention alternative tools. Purpose is clear enough for an agent.

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 on when to use this tool vs the sibling tools (image_edit, image_multi_reference, image_batch_edit). The only usage note is a retry policy, which is not about tool selection. Agents are left to infer from the tool name.

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?

Adds 'Uses paid quota,' a material cost disclosure not present in the annotations. It does not mention output behavior, upload/storage implications, or failure/rate-limit behavior; annotations already cover read-only/idempotency/destructive traits, so the additional burden is modest.

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, front-loaded with the core operation and key constraint, followed by the cost warning. No filler or repetition of schema fields.

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?

Despite seven parameters and no output schema, the description doesn't specify expected output, quality/model semantics, or how to handle the paid quota; it only states the input constraint. An agent would need to guess at substantial behavior.

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 coverage is 0%, so the description must compensate, but it only clarifies image_paths semantics (local 2-10 reference images uploaded together). It leaves prompt, size, model, quality, response_format, and api_key unexplained beyond their schema names/types.

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?

Clearly identifies the operation: generate an image from local reference images, with the count bound 2-10 and the upload requirement. This differentiates it from image_generate/image_edit by input mode, though it never names a sibling or explicitly distinguishes from image_batch_edit.

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 description implies the appropriate use case: when the agent has 2-10 local reference images to use as inputs. It provides no exclusion criteria or explicit guidance on choosing among image_generate, image_edit, and image_batch_edit.

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?

The annotations already declare readOnlyHint=true, and the description aligns by saying 'Read'. The description adds valuable behavioral guarantees: it will not reveal keys and will not contact the provider, which goes beyond the annotation. This provides useful context about safety and external dependencies.

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?

The description is a single, front-loaded sentence that conveys the action, the resource, and the key constraints without any filler. Every word earns its place, and the critical safety qualifier ('without revealing keys') is placed early.

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?

Given the tool's simplicity (no parameters, no output schema), the description is fully complete. It states what the tool does and its behavioral limits, leaving no ambiguity about invocation or expected results. The annotations reinforce the read-only nature, and the description covers everything else needed.

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?

The tool has zero parameters, so the description does not need to explain any. According to the calibration, a baseline of 4 is appropriate for 0-parameter tools. The description adds nothing about parameters because none exist.

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 ('Read'), a clear resource ('PdhAPI configuration'), and adds a distinguishing constraint ('without revealing keys or contacting the provider'). This makes the tool's purpose unmistakable and differentiates it from the unrelated image tools in its sibling list.

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 description does not explicitly state when to use this tool versus alternatives. However, since the sibling tools are all image-generation/editing tools, there is no ambiguity about when this tool applies. Still, no explicit when/when-not guidance is provided, so the score reflects that it is only implied.

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