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

Annotations already declare non-read-only, non-destructive, and idempotent behavior. The description adds the key behavioral detail that existing keywords are preserved, which is essential for distinguishing append semantics. 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?

A single, efficient sentence that conveys the core action and behavior without waste. It is front-loaded with the verb and resource.

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 tool is simple and annotations cover safety, but the description omits any mention of return values or usage context. The presence of an output schema reduces the need to explain returns, yet parameter ambiguity remains a gap.

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 provides no additional meaning for 'refs' or 'keywords'. While the parameter names are somewhat self-explanatory, the description does not compensate for the missing schema descriptions.

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 ('Add'), a resource ('keywords to photos'), and a crucial scope qualifier ('keeping the ones already there'). This clearly distinguishes it from sibling tools like set_photo_title or add_to_album.

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 provided on when to use this tool versus alternatives. The description does not mention context, exclusions, or contrast with other add/set operations.

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 include idempotentHint: true and destructiveHint: false, but the description adds the behavior of creating the album if it does not exist, which is useful. Beyond that, no behavioral traits like ownership or permissions are disclosed, but given the annotations, the description contributes some context.

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 very concise and front-loaded with the main purpose, followed by parameter explanations. The 'Args' section is clear and easy to scan, though it's slightly generated but lacks additional context that might be missing but not overly lengthy.

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 (2 parameters, idempotent and not destructive) an output schema exists, the description is adequate. However, it does not mention any side effects like album creation might fail if album name is invalid, nor how the output schema or return value is used. Still, it's acceptable for a basic operation.

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 schema description coverage at 0%, the description's brief 'album: Album name' and 'refs: Photo uuids or exact filenames' adds meaning. However, it is minimal and doesn't detail expected format for album names or nuances like whether refs must be list of exact matches. It partially compensates for the schema 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 verb ('Add photos') and resource ('to an album'), and mentions creating the album if needed. It distinguishes the tool's purpose from siblings like search_photos or photo_info, though it doesn't explicitly contrast with them.

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, such as add_keywords or set_photo_title. It lacks context about typical workflows or conditions under which adding to an album is appropriate versus not.

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 richly discloses behavioral traits: it is not permanent deletion, it moves items to archive, and the user's perception matters ('the user reads this as deleting their photos'). It also explains the platform limitation (macOS) and that the user must manually empty the album. This goes far beyond the annotations (destructiveHint: true) by clarifying the exact scope of destructiveness and the irreversible-like nature.

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 well-structured and front-loaded with the key warning ('closest thing to deleting'), followed by how it works, then parameter explanations. Every sentence earns its place. Slight verbosity in the line breaks but overall compact. Minor deduction for the blank lines and the informal 'the user reads this as...' phrasing, but it is still tight.

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 tool with two parameters and an output schema present, the description covers the critical context: what it does, how it differs from deletion, when to set confirm, and the operational consequence (user manually empties). The output schema handles return values. This is complete for an agent to decide when and how to invoke it.

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 schema covers 0% of parameter semantics, so the description must compensate. The description explains both parameters: 'refs' as photo UUIDs or exact filenames, and 'confirm' with a clear usage rule. This adds meaning beyond the bare schema types. It doesn't specify exact file name formats or UUID format, but enough for an agent to use it correctly.

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 moves photos into an archive album, removing them from the main library view, and explicitly frames it as 'the closest thing to deleting that macOS allows'. This is a specific verb+resource with a clear effect, and it distinguishes itself from direct deletion and implies why it exists (macOS restriction).

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 clear usage guidance: it states that no app can permanently delete photos, so the user must empty the archive album by hand. It also provides explicit instructions for the 'confirm' parameter: set true only when the user has actually asked for these specific items to go. This tells the agent both when and when not to use the tool, and distinguishes it from other photo tools by its destructive/archive nature.

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, idempotentHint=true, destructiveHint=false, covering the safety profile. The description adds valuable context by listing the specific aspects being diagnosed, which goes beyond the annotations and clarifies the tool's scope.

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 sentences with no filler. The first sentence lists the diagnostic targets, the second gives a direct usage directive. Every word earns its place, and the most important action ('Diagnose') is 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?

For a zero-parameter diagnostic tool with rich annotations and an output schema, the description fully covers purpose, scope, and usage timing. Nothing essential is missing for an agent to select and invoke 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?

This tool has zero parameters, so the baseline is 4. The description correctly avoids inventing parameter details and instead focuses on what the tool checks, which is sufficient for a no-argument diagnostic.

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 a specific verb ('Diagnose') and names the exact resources it checks: macOS, Full Disk Access, library, index, and write status. This clearly differentiates it from sibling tools like search_photos or library_stats, which focus on other operations.

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 when to use it: 'Run this first when anything misbehaves.' This gives clear timing guidance. It lacks explicit when-not-to-use or alternative tool mentions, but the context is still strong.

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 the annotations by disclosing performance behavior ('Slow for iCloud-only assets: each one is downloaded first') and privacy behavior ('Nothing is uploaded anywhere'). It also implicitly conveys that this is a non-destructive copy operation, consistent with destructiveHint=false. It does not contradict annotations and adds useful context about side effects.

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: the first sentence states the core purpose. The subsequent sentence adds a crucial performance caveat in plain language. The Args section is short, scannable, and uses line breaks for each parameter. Every sentence earns its place without fluff.

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 covers the essential calling details (refs, destination, iCloud caveat, setup) and is backed by annotations for safety and idempotency. It omits minor operational specifics such as whether the directory is created automatically or how duplicate filenames are handled, but these are not critical for basic invocation. The presence of an output schema also lessens the need to describe return values.

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%, but the tool description includes a dedicated Args section that explains both parameters in non-schema terms: refs accepts 'Photo uuids or exact filenames', directory is described as 'Absolute destination folder' with an explicit default. This fully compensates for the missing schema descriptions and gives the agent actionable format guidance beyond the raw property 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?

The description states a specific action ('Export'), resource ('full-quality originals'), and destination ('folder on this Mac'). This is unambiguous and distinguishes it from sibling tools that search, view, archive, or modify photos. No other sibling performs local copying of originals, so the purpose is uniquely and clearly identified.

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 clearly implies the tool is used whenever full-quality photos need to be downloaded as files to this Mac, and it adds useful context about slowness for iCloud-only assets. However, it never explicitly states when to use it over alternatives, when not to use it, or names any sibling tool as a fallback. The usage context is inferred rather than spelled out.

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 indicate non-read-only, non-destructive, idempotent behavior. The description adds the key context that the tool can both add and remove a favorite state, which is useful. However, it does not disclose error behavior, permission requirements, or effects on non-existent refs.

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 extremely concise, with no filler. The args section is clearly formatted and each line adds value. It earns its place entirely.

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 small 2-parameter tool with an output schema and rich annotations, the description covers the basics. However, it lacks any usage context or error/edge-case information, and does not reference sibling tools, which could leave an agent uncertain about the best tool for a given request.

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 the description must compensate. It explains that 'refs' accepts photo UUIDs or exact filenames, and that 'favorite: False' un-favorites. This is essential semantic detail not present in the schema, though filenames could be more specific (e.g., extension format).

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 action ('Heart photos') and its inverse ('remove the heart'), with a specific resource ('Photos'). It is easily distinguished from sibling tools like set_photo_title or add_to_album.

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 provided on when to use this tool versus alternatives. There is no mention of use cases, prerequisites, or exclusion conditions. The description only explains what the tool does, not when to choose it.

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, idempotentHint=true, and destructiveHint=false, so the tool's safety profile is well established. The description adds useful context about what metrics are covered but does not disclose any additional behavioral traits such as response size, potential latency, or how the library is determined. With annotations covering the core behavior, a score of 3 is appropriate.

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 sentence that packs specific, useful details into a compact statement. Every clause contributes meaning, and the structure is easy to parse. There is 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?

With no parameters, strong annotations, and an output schema present, the description only needs to communicate what the tool reports, which it does comprehensively. It names the categories of information (totals, albums, named people, indexing, iCloud-only content) and leaves return format details to the output schema. 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?

The tool takes zero parameters, so the baseline for parameter semantics is 4. The description does not need to explain parameter meaning since there are none. The schema coverage is effectively 100% because the parameter list is empty, so nothing is left undocumented.

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 identifies the resource (the library) and the specific kind of information provided (totals, albums, named people, indexing status, iCloud-only content). However, it lacks an explicit verb like 'get' or 'retrieve', so it describes the subject matter rather than stating the action, making it slightly less actionable than an ideal definition.

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 no guidance on when to use this tool versus alternatives. While no sibling tool appears to perform the same function, the description does not state when this should be chosen, nor does it mention any prerequisites or context. It is left entirely to the agent to infer that this is the go-to for library-level statistics.

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 tool is clearly safe. The description adds context about the closed vocabulary, which helps explain the tool's purpose but does not detail response behavior or pagination. This is adequate given the strong 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, front-loads the core purpose, provides a practical usage context, and then documents parameters in a clear block. Every sentence earns its place with no 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?

Despite lacking output schema details in the description, the presence of an output schema means return format is not needed. The tool's purpose, usage trigger, and all parameter semantics are fully covered, making it complete for an agent to invoke 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?

The description explicitly documents each parameter in the Args section: 'starts_with' is defined as a prefix filter and 'limit' as the maximum number of terms returned. Since schema description coverage is 0%, this full compensation is essential and well executed.

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 that the tool lists the visual words the library knows, tying it to Apple's closed vocabulary. It explicitly differentiates itself from search tools by positioning it as the way to discover valid words when a search returns nothing.

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 a specific use case: 'When a search finds nothing, this is how to discover the word it does understand instead.' This implies when to use it relative to search, but it does not enumerate alternative tools or explicit when-not-to-use conditions. Still, the guidance is clear enough for an agent.

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?

Given the annotations already declare the operation read-only and idempotent, the description adds genuinely useful behavior: it renders thumbnails, returns an image, and works for iCloud-only photos by reading Apple's local thumbnail cache rather than the original. This tells the agent an important implementation detail beyond the structured hints.

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: one functional summary, one targeted usage instruction, one implementation note, and two parameter definitions. Every sentence earns its place and the most important information is 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?

For a simple two-parameter rendering tool, the description covers what the tool does, when to use it, how it behaves for iCloud photos, and both parameter meanings. The only minor gap is that with no output schema it does not specify how multiple refs are packaged in the returned image output, though the workflow is still clear.

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 fully compensates by explaining that refs accepts photo UUIDs from search results or exact filenames, and that size is the longest edge in pixels with a 128-2048 range. This is exactly the meaning an agent needs and is not present 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 opening sentence names the specific action ('renders each one') and the resource (photos), and explicitly states the output is an image. This distinguishes it from search_photos and export_originals, which either locate or export originals rather than render thumbnails.

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 an explicit trigger: use on the top few results of every search before answering a 'find my photo of X' question. It does not explicitly mention when not to use it or name alternatives, but the workflow context is 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 declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is clear. The description adds little beyond the annotations, only hinting at the breadth of data ('everything known'), but doesn't disclose potential privacy implications or rate limits. No contradiction.

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: one functional summary and one parameter explanation. No wasted words, and the key action and resource are 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?

For a simple single-parameter read-only tool with rich annotations and an output schema (not shown), the description covers what the tool returns and how to specify the target photo. It lacks guidance on when to choose this over siblings, but overall it is sufficiently complete for an agent to invoke 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 0%, so the description must carry the burden. It does by explaining that 'refs' are 'Photo uuids or exact filenames', which is far more informative than the schema's bare 'Refs' title. This effectively compensates for the lack of schema descriptions.

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 'Everything known' and lists the exact kinds of information (metadata, ML labels, place, albums, faces, text), making it obvious that this tool retrieves comprehensive metadata for a given photo. It is clearly distinct from siblings like search_photos or look_at_photos.

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 states what the tool does but does not explicitly say when to use it over alternatives. It implies usage for retrieving detailed photo information, but there is no mention of exclusions or comparisons to look_at_photos/edit 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 this as read-only, idempotent, and non-destructive. The description adds valuable behavioral context beyond annotations: that the search leverages an on-device index, that filters narrow before ranking, and that natural language phrases work best. This gives the agent a useful model of how the tool behaves internally.

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 efficiently structured: a two-sentence overview followed by a terse Args list. Each line is informative and jargon-free, with no redundant fluff. It earns every word while remaining skimmable.

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 having 12 parameters and no schema descriptions, the description covers all parameters, provides usage examples, and specifies search behavior. Since an output schema exists, return values need no elaboration. The tool is fully specified for an agent to invoke 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?

With 0% schema description coverage, the description carries the full burden of parameter documentation. It defines every parameter in plain language, including formats (ISO date, inclusive bounds), allowed values (e.g., screenshots: include/exclude/only), and default behavior (query empty browses by filter). This is exemplary compensation for missing schema descriptions.

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 opens with a specific verb and resource ('Search your entire Apple Photos library') and notes the use of Apple's on-device index. This clearly distinguishes it from sibling tools like look_at_photos or library_stats, which serve different purposes.

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 concrete usage context: recommends natural visual phrases, explains that filters narrow before ranking, and even describes browsing behavior when query is empty. It does not explicitly exclude alternatives, but the guidance is clear enough for correct selection among 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?

Annotations already indicate this is a non-readonly, non-destructive, idempotent operation. The description does not add behavioral context such as permission requirements or whether the existing description gets replaced. No contradiction with annotations 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?

The description is a single concise sentence that directly states the action. It is appropriately sized for a simple tool, though it omits useful details. The structure is straightforward and 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?

For a simple tool with an output schema, the description is minimal but misses key parameter semantics, particularly what 'ref' refers to. The agent may struggle to know how to fill the required parameters correctly. The lack of usage context further 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 0% schema description coverage, the description needed to explain the 'ref' and 'description' parameters, but it only mentions caption. The meaning of 'ref' (likely a photo identifier) is left undocumented. Therefore the description does not compensate for the schema's lack of detail.

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 'Set' with the resource 'one photo's description/caption', making the operation clear. It is implicitly distinguished from sibling tool set_photo_title which handles titles, though it doesn't explicitly name the alternative.

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 about when to use this tool versus alternatives like set_photo_title or add_keywords. The description only states the action, leaving the agent to infer usage context. Since there are no exclusions or conditions, this is below average.

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 carry the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true), and the description states a mutation ('Set') that is consistent with them. It adds the single-photo scope beyond what annotations convey, but discloses no additional behavioral context such as overwriting behavior, auth requirements, or response characteristics. 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?

A single five-word sentence carries the entire description with absolute economy. Every word earns its place and there is zero filler, making it optimally scannable.

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 tool is simple (2 required scalar params, annotations provided, output schema present) and the description covers the basic purpose, so nothing critical is missing. However, the ref parameter is undefined beyond being a photo reference, and there is no sibling differentiation — gaps that matter given 0% schema description coverage.

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 the description must compensate. 'one photo's title' meaningfully maps title to the new title text and ref to the target photo, but ref remains vague — no format, type of identifier, or example is given. The explanation adds some value but does not fully resolve parameter ambiguity.

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 'Set one photo's title' names a specific verb (set), resource (a photo), and attribute (title), and adds the scope delimiter 'one photo.' It is clear about what the tool does, and the title-vs-description distinction from sibling set_photo_description is implicit, though it never names or contrasts the sibling 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 implies usage only through the tool's name and one-line summary; it gives no explicit when-to-use, when-not-to-use, or alternative guidance. With near-identical sibling set_photo_description available, an agent gets no help distinguishing which tool to pick.

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