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

With no annotations provided, the description fully discloses behavioral traits: high concurrency (4-8 images), default limit of 100, pagination behavior, and performance trade-offs of fast_mode. It also implies read-only analysis, consistent with the tool's purpose.

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 concise, with three front-loaded sentences. Each sentence adds crucial information: the main function, pagination instructions, and use case. No filler or redundant content.

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 7 parameters and an output schema, the description covers the essence: batch behavior, pagination, performance modes. It does not need to repeat schema details but provides sufficient context for an agent to use 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?

Although schema coverage is 100% (baseline 3), the description adds value by explaining concurrency behavior not in schema, clarifying fast_mode's performance trade-off, and describing pagination with 'nextOffset'. This exceeds schema documentation.

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: batch analyzing all images in a folder. It specifies the resource (folder), action (analyze with high concurrency), and outcome (quality scores and judgements). This distinguishes it from sibling tools like photographi_analyze_photo, which handles single images.

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 clear usage guidance: pagination with 'limit' and 'offset', and handling 'nextOffset'. It also recommends the tool for assessing overall quality distribution of a shoot. However, it does not explicitly state when to use alternatives, though this is implied by sibling names.

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?

No annotations are provided, so the description carries full responsibility for behavioral disclosure. It describes the fast_mode parameter's trade-off between speed and forensic precision, which is a key behavioral aspect. However, it does not mention any other side effects (e.g., file modification) or prerequisites, though the tool appears to be read-only. The description is fairly transparent but could be more explicit about non-destructive 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 two sentences long. The first covers purpose and output, the second provides usage guidance and sibling differentiation. Every sentence is essential; no unnecessary 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?

Given the detailed input schema (5 parameters with descriptions, enums, defaults) and the presence of an output schema, the description is complete. It explains the tool's purpose, what it returns, and when to use it versus the sibling tool. No additional information is needed for successful tool invocation.

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 high (80%), so baseline is 3. The description adds no additional parameter-level detail beyond what the schema already provides (e.g., metrics list, fast_mode behavior). It does summarize the overall output, which is helpful but not specific to parameter semantics. Thus, the description adds minimal value 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 clearly states the tool analyzes a single photo for technical quality metrics like sharpness, exposure, noise, etc., and returns an overall score, judgement, and per-metric breakdowns. It distinguishes itself from the sibling batch tool 'photographi_analyze_folder' by explicitly noting it is for individual images.

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 'Use this for detailed inspection of individual images' and provides the alternative 'For batch analysis, use photographi_analyze_folder.' This gives clear when-to-use and when-not-to-use 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?

With no annotations, the description discloses key behaviors: moving files, threshold logic, batch size, mode options, and fast mode. It is transparent about what happens to images above/below threshold, though it does not mention that moving is potentially destructive.

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 concise at 5 sentences, front-loaded with the main action, and includes essential details without redundancy.

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 7 parameters and an output schema, the description covers the core functionality, modes, pagination, and fast mode. It does not explain the subject_detection parameter but the schema covers it. Overall, it is nearly complete.

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 high (86%), so baseline is 3. The description adds marginal value by explaining defaults and behavior (e.g., threshold logic, fast mode speed), but most parameters are already described in 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 clearly states it 'Culls low-quality images by moving them to a culled_photos subfolder', specifying the verb (cull) and resource (images). It differentiates from siblings like photographi_threshold_cull by detailing modes and threshold behavior.

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 explains when to use (culling low-quality images) and provides context on default behavior, modes, and pagination. However, it does not explicitly compare to sibling tools or state when not to use.

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?

No annotations exist, so description bears full burden. It discloses the algorithm (K-Means), read-only nature (extraction), and output format. Lacks details on error handling or resource usage, but is adequate for a simple extraction tool.

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 sentences, each serving a distinct purpose: purpose+method, output+default, usage guidance. Front-loaded, 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?

Given output schema exists, return value explanation is adequate. Tool is simple with 2 params; description covers key behavior. Minor omission: no mention of valid image formats or error cases, but overall 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 covers image_path with description but not colors. Description adds default value and output format context for colors, and implies image_path is absolute, adding value beyond schema's 50% coverage.

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 clearly states it extracts a color palette from a single image using K-Means clustering, and lists output as hex codes. It distinguishes from sibling tools like photographi_get_folder_palettes (folder-level) and photographi_analyze_photo (broader analysis).

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?

Provides a use case ('design inspiration or color grading reference') but does not explicitly exclude alternatives or specify when not to use this tool over siblings like photographi_get_folder_palettes for batch palette extraction.

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?

No annotations provided, so description carries full burden. It states default processing of 20 images and that it returns a map. However, it lacks details on error handling, folder validity, or the role of the 'colors' parameter, leaving some behavioral ambiguity.

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 concise with three clear sentences: function, default behavior, and use case. No redundant information, but the structure could be improved by explicitly linking parameters.

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 4 parameters and an output schema, the description adequately covers pagination but misses the 'colors' parameter explanation. The output schema existence reduces the need for return value details, but the missing parameter info reduces completeness.

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 only 25% schema description coverage, the description adds minimal value. It explains pagination via limit/offset but does not explain the 'colors' parameter or the relationship between limit and default processing count. The description partially compensates but leaves a significant 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 clearly states the tool extracts color palettes from multiple images in a folder, using the verb 'Extracts' and the resource 'color palettes'. It distinguishes from siblings like 'get_color_palette' (single image) via the folder scope, though not explicitly.

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 mentions pagination using limit/offset but does not provide explicit guidance on when to use this tool versus alternatives (e.g., use get_color_palette for a single image). No exclusion criteria or when-not-to-use advice.

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?

No annotations provided, so description bears full burden. Describes detection and return of labels, implying read-only behavior. Lacks explicit statement about no side effects, but adequately clear for a detection tool.

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 efficient sentences plus a one-sentence alternative mention. No fluff; main purpose and usage guidance front-loaded.

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?

Simple detection tool with one parameter and output schema provided. Description fully covers purpose, usage, and alternative. No missing 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 covers 100% of parameters with clear detail ('Absolute path to RAW/JPEG/TIFF.'). Tool description adds no extra parameter information beyond schema, meeting baseline for high coverage.

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 states it detects objects using YOLO and returns object labels. Distinguishes from sibling tool 'photographi_analyze_photo' by contrasting quick indexing vs. full analysis.

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?

Explicitly recommends use 'for quick scene indexing or content-based search' and directs to 'photographi_analyze_photo' for alternative cases. Clear when and when not to use.

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, the description carries full burden. It discloses high concurrency, limit of 100, fast_mode performance trade-off (4-8x faster vs. forensic precision), and that it returns detailed metrics. This is thorough for a non-destructive read tool.

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 concise with five sentences, front-loaded with the primary action, then adds details and an alternative. Every sentence adds value without redundancy.

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 8 parameters and an existing output schema, the description covers main purpose, use cases, concurrency, and limit. It does not mention pagination (offset) or subject detection/model_size, but these are secondary and schema covers them. Still, it is fairly complete.

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 high (88%), so baseline is 3. The description adds context about the limit parameter (high concurrency, up to 100 per call) but does not elaborate on other parameters beyond what the schema already provides.

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 ranks photos by technical quality and returns the top_n best images. It distinguishes itself from the sibling tool photographi_analyze_folder by suggesting the latter for full folder analysis.

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?

Explicitly states ideal use cases: burst sequences or finding hero shots. Mentions high concurrency and default limit of 100 images per call. Provides explicit alternative: use photographi_analyze_folder for full folder analysis.

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, the description carries full burden. It discloses side effects (moving files to rejects), mode options, processing limit, and fast mode behavior. It transparently explains default behavior and consequences.

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?

Description is concise (two sentences), front-loaded with core action, and every sentence adds value. No redundant 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?

Given 7 parameters, low schema coverage, and no annotations, description covers threshold behavior, defaults, mode, processing limit, and sibling comparison. But misses explanation for enable_subject_detection and offset. Output schema exists, so return format not 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?

Schema coverage is 43% (3 of 7 params described). Description adds meaning: explains min_confidence default, processing 100 per call, mode options. However, parameters like enable_subject_detection, limit, and offset are not explained beyond 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?

Description clearly states binary threshold culling for images, moving low-confidence ones to 'rejects' subfolder, and distinguishes from sibling photographi_cull_photographs by higher default threshold and different folder name.

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?

Description explicitly compares with sibling tool and provides context for when to use this stricter filtering. It mentions processing 100 images per call and mode options, but does not explicitly state when not to use.

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