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

Beyond the annotations, the description discloses meaningful behavioral traits: idempotent behavior with existing derived revisions, preset-to-recipe hash equivalence, ICC color profile dropping for certain encode formats, and warning-as-not-error semantics. It also clarifies that a new revision is issued. This goes well beyond what readOnlyHint, destructiveHint, and idempotentHint already communicate.

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 packed with essential information but remains well-structured and front-loaded with the core purpose. Each sentence contributes unique value: input constraints, sibling tool pointers, idempotence, and an edge-case warning. No filler is present.

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 complex transform tool, the description covers input selection, mutual exclusivity, batch behavior, idempotence, encoding caveats, and where to find operation catalog details. An output schema exists, so return-value details need not be duplicated. The description is complete enough for an agent to call the tool correctly in both single and batch scenarios.

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?

Even though schema description coverage is 100%, the description adds critical parameter semantics not encoded in the schema: recipe structure with operations applied in order, at most one encode operation and it must be last, the exact one-of relationship, batch size limit of 64, and per-item failure isolation. The note about ICC profile behavior further clarifies the recipe parameter's practical effects.

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 begins with a specific verb and resource: 'Apply a transform recipe at full resolution and issue a new revision.' It clearly distinguishes this from siblings like render_preview and export_asset by emphasizing full-resolution processing and revision creation. The operation's core input alternatives are also stated, leaving no ambiguity about what the tool does.

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 gives explicit usage context: exactly one of recipe/preset and exactly one of revision_id/revision_ids, plus batch limits and failure semantics. It also points to sibling tools list_operations and explain_operation for prerequisite knowledge. However, it does not explicitly state when not to use this tool versus siblings like render_preview, so it stops short of a full 5.

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 discloses key behaviors: scaling to a 640px long edge, an 8px gap, placement of A and B, and the diff mode's requirement for identical dimensions plus its output metrics. Annotations provide idempotentHint=true and destructiveHint=false, and the description does not contradict them. It adds context about the output format (JPEG) and diff-specific metrics, which is valuable 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?

The description is compact and front-loaded with the primary behavior, then pivots to the diff variant. Each sentence serves a purpose—no filler. It could be slightly more concise, but it remains efficient and well-structured.

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 moderate complexity (3 params, output schema present, annotations provided), the description covers the essential aspects: main usage, diff mode requirements, output format, and key behavioral details. It doesn't discuss error conditions or performance limits, but these are not critical for an agent to invoke the tool correctly. The presence of an output schema means the description need not elaborate on return values, and it still explains diff metrics.

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 100%, so the schema already documents each parameter thoroughly (layout enum, revision IDs, placement). The description adds the scaling and gap behavior, but these are tool-wide behaviors rather than parameter-specific semantics. It does reinforce the diff layout's dimension requirement, which is already in the schema. The description adds marginal value, so a baseline 3 is appropriate.

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 clearly states the tool's function: it scales two revisions, composes them on a canvas (side by side or stacked), and returns a JPEG. It also explicitly differentiates the diff mode, which produces a pixel-difference heatmap. This is specific and distinct from sibling tools like apply_transform or detect_document, which focus on transformation or analysis rather than visual comparison.

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 provides a clear use case: 'Useful for before/after or A/B visual checks.' It also explains when the diff layout is appropriate (when A and B share exact dimensions). However, it doesn't explicitly mention when not to use this tool or name alternatives, though among the siblings none serve the same comparison purpose, so the guidance is adequate.

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 already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds valuable behavior beyond that: coordinate ordering (tl, tr, br, bl), post-EXIF-orientation coordinates, output_size_hint semantics, min_area_ratio constraints, and the exact warning reasons when quad is null. This is rich, non-redundant behavioral detail.

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 sentences, each earning its place: purpose and analogy, coordinate/output semantics, and parameter/warning behavior. It front-loads the core action and keeps supporting details compact, with no filler or repetition.

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 annotations, full schema coverage, and presence of an output schema, the description covers everything an agent needs: operation type, coordinate system, ordering, output sizing, parameter defaults, and failure/warning semantics. No important calling decision is left unexplained.

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?

Input schema coverage is 100%, so the baseline is 3. The description still adds meaning to min_area_ratio as 'the smallest fraction of the frame a candidate may cover', and clarifies that output_size_hint matches what perspective will produce. It does not add much to revision_id, but that is already well covered by the schema.

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: 'Detect the dominant quadrilateral ... in a revision with a contour-based search', and clarifies the return as a 'ready-to-paste perspective operation'. It also distinguishes itself from sibling detect_tilt by drawing the perspective/rotate analogy, so an agent can tell what this tool uniquely does.

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 gives strong context: it is read-only, never modifies the image, and a null quad means 'do not correct'. It also relates the tool to perspective via detect_tilt, which implies when to use it. It does not spell out explicit exclusion cases or name more alternatives, so it stops short of the strongest possible guidance.

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?

Beyond the readOnlyHint/idempotentHint annotations, the description explicitly says it never modifies the image, describes processing stages (Canny/Hough then projection-profile refinement), discloses response-size behavior (score curve omitted by default), and defines the null recommended-angle sentinel. This gives an agent strong expectations for side effects and outputs.

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 front-loaded with purpose and method, and each clause adds useful context. It is slightly dense and contains a minor punctuation issue ('roll,' followed by 'Set'), but no sentence is 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?

With an output schema present and annotations covering safety/idempotency, the description supplies the remaining operational context: algorithm, default response size, read-only behavior, and the meaning of null. An agent has enough to call the tool correctly.

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 100%, and the schema already explains revision_id, max_abs_angle, and include_score_curve. The description reinforces include_score_curve's behavior and adds 'to keep the answer small', but it contributes little beyond the schema and does not deepen revision_id or max_abs_angle semantics.

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 opening states a specific verb and resource: 'Detect the tilt (roll) of a revision' rather than a generic or tautological phrase. It also details what the tool returns (horizontal-only and vertical-only estimates, optional score curve), so an agent can distinguish it from siblings like detect_document.

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?

Clear context is given: the tool is for measuring roll/tilt of a revision, and the description explains how to interpret disagreement between estimates and when to set include_score_curve=true. However, it does not explicitly name alternatives or state when not to use this tool versus siblings such as apply_transform or detect_document.

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 already declare readOnlyHint=true, but the description goes further: it states 'Read-only' explicitly, describes support for preset names, and explains the structured error response for unknown names listing all valid operations. This adds behavioral context beyond the annotations, covering error handling and preset behavior.

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 approximately 80 words, composed of three sentences. It front-loads the main purpose ('Full reference for one recipe operation'), then details content, presets, and errors. Reasonably concise and logically structured, though it could be slightly tighter.

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 read-only reference tool with one parameter and an output schema, the description covers return content (parameters, examples, gotchas), preset handling, and error behavior (unknown names return a structured error with valid operations). All essential information for correct invocation is present.

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 only parameter, 'operation', has a schema description explaining it as the op name to write in the format {"op": "..."}. Schema description coverage is 100%, so the description adds no additional meaning about the parameter itself; it focuses on the return value. Baseline of 3 is appropriate.

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 clearly states the tool's purpose: 'Full reference for one recipe operation' with detailed content (parameters, examples, gotchas). It also covers preset handling and error behavior, distinguishing it from sibling tools like list_operations. The verb 'explain' and resource 'operation' are specific and unambiguous.

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 usage for when detailed information about a specific operation is needed, contrasting with listing all operations. It does not explicitly name an alternative, but the context 'one recipe operation' and the error fallback listing all valid operations provide clear guidance. No explicit exclusions, but sufficient context.

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 already provide destructiveHint=true and readOnlyHint=false. The description adds meaningful behavioral detail: it refuses to overwrite unless overwrite=true and instructs the agent to ask the user first. This goes beyond the annotations and helps the agent avoid unintended data loss.

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 tight sentences: the first states the core operation, and the second front-loads the most important safety constraint. There is no filler or repetition of schema fields, making it highly efficient.

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 simple three-parameter tool with an output schema and clear annotations, the description covers the essential behavior: what the tool copies, where it copies to, and the overwrite guardrail with user-consent guidance. Nothing critical for invoking it correctly is missing.

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%, so the schema already documents all three parameters. The description adds value by clarifying the overwrite behavior and the user-consent requirement, but it does not substantially deepen meaning for revision_id or dest_path beyond the schema.

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 uses a specific verb ('Copy') and resource ('a revision's bytes') and states the destination context ('out of the workspace to a destination path'). This clearly distinguishes it from sibling tools like import_asset, which would perform the reverse operation.

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 purpose makes the tool's usage context clear, but the description does not explicitly say when to prefer this tool over alternatives or mention any exclusions. The overwrite caveat is behavioral guidance rather than selection guidance, so usage direction is mostly implied.

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 goes beyond annotations by detailing the deterministic and idempotent behavior (same params produce byte-identical PNG and return existing revision). It also clarifies what the mask represents (white = full application, black = none) and that gradients use dimensions while ranges use pixels. The idempotentHint annotation is confirmed and expanded with specifics.

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 moderately long but every sentence serves a purpose: it defines the function, parameter kinds, output semantics, usage example, and idempotency. The front-loaded summary of kinds is efficient, and the JSON usage example is compact yet informative. No fluff or repetition.

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 complexity (13 parameters, 4 kinds) and presence of output schema, the description covers key aspects: output semantics, idempotency, and usage integration. It omits explicit return value format (though output schema exists) and some edge cases, but the examples and schema descriptions cover most. The description is sufficient for an agent to call it correctly.

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 100% with detailed descriptions for each parameter including default values and units. The description adds clarity by grouping parameters by kind and explaining the common semantics (like feather behavior) but does not add substantial new information beyond the schema. The description's parameter list matches the schema and provides complementary context (e.g., which parameters apply to which kind), but this is largely redundant.

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 clearly states the tool's function: generating a deterministic grayscale mask as a new PNG revision with exact dimensions from a reference. It enumerates four distinct mask kinds with their parametersholistic details, and explains the white/black semantics. This distinguishes it from siblings like render_preview or apply_transform by focusing on mask generation.

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 explicitly explains how to use the result: referencing the returned revision_id in tone/filter operations with a concrete JSON example, and how to visualize it with render_preview overlay. It does not explicitly mention when not to use it, but the detailed operation contracts and idempotency note provide clear context for typical use cases. The alternatives are implied by sibling tools, and the usage examples are sufficient.

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?

Goes well beyond the idempotentHint annotation by describing immutable revisions, partial batch failures, and the already_derived_from warning. These behaviors are not inferable from annotations alone and are critical for correct invocation.

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?

Four tightly packed sentences with no fluff. The core contract, parameter choice, and edge cases are all covered efficiently, and the most important information comes first.

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?

Covers the invocation contract, failure mode, idempotency, and duplicate-recipe warning. With an output schema present and annotations providing the safety profile, nothing essential is missing for correct use.

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 100%, so the schema already documents path/paths exclusivity, batch size, and failure behavior. The description reinforces exactly-one selection and batch failure semantics but adds little new parameter-specific information beyond the schema.

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: 'Import a local image file into the workspace and issue an immutable revision.' This clearly distinguishes it from sibling tools like export_asset by direction and outcome.

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 explicit guidance for the two mutually exclusive invocation modes (path vs paths) and explains batch failure behavior. It does not name alternative sibling tools explicitly, but the import/export contrast and local-file scope make the intended use clear.

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 already establish readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds meaningful behavioral detail by listing the specific metadata categories inspected, including the noteworthy GPS/PII check, which goes beyond the annotation fields.

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 compact sentence that front-loads the core action and then uses a colon-delimited list of concrete inspected properties. There is no filler or redundant restatement of the tool name.

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 single simple parameter, the presence of an output schema, and annotations that fully define the operation's safety and idempotence, the description is complete enough for an agent to select and invoke the tool correctly. It even calls out the privacy-relevant GPS/PII aspect, which is useful context.

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 only one parameter, revision_id, and the schema description covers it fully (100% coverage), including the 'rev_...' format. The description adds no additional parameter-specific semantics, so the baseline of 3 is appropriate.

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 uses a specific verb ('Inspect') and a specific resource ('a revision'), then enumerates exactly what is inspected: dimensions, MIME type, byte size, alpha/ICC, EXIF, and GPS/PII presence. This clearly distinguishes it from siblings like render_preview or compare_revisions.

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 its use case (metadata inspection of a revision) but does not explicitly state when to prefer it over alternatives or when not to use it. There are no exclusionary or comparative statements referencing sibling tools.

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 already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds that it lists revisions and includes specific data fields, which is useful context but does not disclose behavioral traits like pagination or ordering. With annotations covering safety, a 3 is appropriate; no contradiction exists.

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 concise sentence that front-loads the action and includes only essential information. No filler or redundancy; every word contributes to clarity.

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 simple read-only tool with one well-documented parameter, an output schema, and safety annotations, the description is sufficient for correct invocation. It does not explain domain-specific terms like 'workspace ledger', but that is likely implicit in the system context.

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% for the single parameter asset_id, which includes a clear description (filter by asset_id, omit for all). The tool description adds no additional meaning beyond what the schema already provides, so the baseline 3 is correct.

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 (List) and resource (revisions in the workspace ledger), and enumerates returned fields (lineage, recipe hash, dimensions, sizes). It distinguishes from siblings like list_operations by focusing on revisions. However, the tool name 'list_assets' suggests assets rather than revisions, creating slight ambiguity about what is being listed.

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 provides no guidance on when to use this tool versus alternatives, nor any exclusions or conditions. An agent must infer usage from the name and description alone; there is no explicit 'use when...' or 'instead of...' context.

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 already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds behavioral context by specifying what the catalog contains and that category narrows the output. It also repeats the read-only property, which is consistent 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 compact and front-loaded: it states what the tool returns, then covers the optional filter, the sibling tool to use for more detail, and the read-only nature. Every sentence earns its place with no redundancy or filler.

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 simple single-optional-parameter interface, an output schema, and annotations that already convey safety, the description provides everything needed to invoke the tool correctly. It includes the category values, the filtering behavior, and the fallback tool for deeper detail. Nothing essential is missing.

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%, so the schema already fully documents the category parameter, including its allowed values and default behavior. The description adds 'narrows the list' but does not materially go beyond the schema. Baseline 3 is appropriate.

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 clearly states a specific purpose: listing every operation in the recipe vocabulary with one-line descriptions, parameter hints, and preset names. It differentiates itself from explain_operation by explicitly directing users there for full schema details. This is far beyond a vague or tautological description.

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 states the optional category filter and its allowed values, and explicitly names explain_operation as the alternative when full schema details are needed. This gives an agent clear guidance on when to use this tool versus its sibling. The read-only note reinforces safe usage.

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 already declare idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: the preview is returned inline plus a file path, overlay lines are drawn only on the preview and never on apply_transform output, and the ICC color profile dropping behavior for non-jpeg encode formats is disclosed as a warning. This goes beyond the annotations and helps the agent anticipate side effects and edge cases.

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 dense but well-organized: it front-loads the core purpose and return behavior, then explains optional parameters and edge cases. Every sentence adds information. It is longer than a typical description, but the complexity of the tool (multiple overlays, conditional mask_revision_id, ICC profile caveat) justifies the length. Slight redundancy with the schema's parameter descriptions prevents a 5.

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 complexity (6 parameters, conditional requirements, multiple overlay modes, output schema present), the description covers all essential behavioral aspects: what is returned, when to use it, how to choose long_edge, how overlays work, the mask_revision_id condition, and the ICC profile warning. The output schema exists, so return values need not be described in detail. Nothing critical is missing for an agent to call this tool correctly.

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%, so the schema already documents all parameters. The description adds meaning beyond the schema by explaining the purpose of long_edge (768 is too small for reading text, raise to 1568), the exclusivity of recipe/preset, and the conditional requirement of mask_revision_id for overlay='mask'. It also clarifies that overlay lines never appear on apply_transform output. This is meaningful added value, though the schema already carries the basic semantics.

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 ('Render'), a specific resource ('a recipe as a small JPEG preview'), and the purpose ('so the composition can be checked before committing to apply_transform'). It clearly distinguishes itself from the sibling apply_transform by emphasizing it is a preview-only operation. The description also names the key alternatives (recipe or preset) and the optional overlay modes, making the tool's role unambiguous.

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 explicitly says when to use this tool ('before committing to apply_transform') and names the sibling apply_transform as the alternative. It also gives concrete guidance for parameter choices: raise long_edge to 1568 when reading text, use overlay modes for composition guides, and use overlay='mask' with mask_revision_id for mask coverage. This is explicit, actionable usage guidance.

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