Moonscroll

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

There are no annotations, so the description carries the full burden. For a generative/mutating tool it says nothing about determinism, whether the idea is persisted, auth requirements, or rate limits. Only the seed input format is hinted at.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with the action front-loaded and the optional parameter mentioned second. No wasted words, though it is arguably too terse for the gaps it leaves.

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?

An output schema exists, so return values need not be described. However, the required brand_hash semantics, the relationship to get_idea/list_ideas, and any behavioral expectations for a generation call are all absent, leaving the definition under-specified.

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 does add a useful range for 'promotion_rating 0-10', but the required 'brand_hash' parameter is left completely unexplained (what a brand hash is, where to obtain it).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Generate one idea for a brand'), and the singular scope ('one idea') implicitly contrasts with the script and list/get siblings. It does not explicitly name which sibling it substitutes for, so it falls short of a 5.

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 indication of when to use this versus get_idea, list_ideas, or generate_script, and no prerequisites or context are given. The agent must infer the workflow entirely from the name.

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

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

No annotations, so description carries full burden. It discloses the side effect that brand_hash creates one idea first, which is useful. However, it omits whether generation is idempotent, permission requirements, or handling of conflicting inputs.

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 compact sentences, front-loaded with the main action. No redundant text; the optional parameter note is appended efficiently.

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 tool with no annotations, an output schema, and zero parameter descriptions, the description is minimal but covers the essential invocation paths. It leaves gaps about input requirements and behavioral edge cases, but is adequate for a basic generation call.

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 description must compensate. It names all three parameters and gives the range for promotion_rating (0-10). It implies you need either idea_hash or brand_hash, but doesn't explain hash formats or what happens if both are provided.

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 'Generate' and resource 'script', distinguishing from siblings like generate_idea and get_script. Clarifies two input paths (idea_hash or brand_hash) and the side effect of creating an idea first. Lacks explicit sibling routing but implicit differentiation is clear.

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?

Indicates two ways to invoke (from idea_hash or brand_hash) but doesn't say when to choose one over the other, nor when to prefer this over get_script or generate_idea. Implied usage only.

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, so the description carries the full disclosure burden and delivers little: it does not state what happens when the hash is unknown, whether the audience must be owned by the caller, or any auth requirement. For a lookup keyed by an opaque hash, error behavior is exactly what an agent needs to know and it is absent.

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 waste-free sentence with the action front-loaded. It is appropriately sized for a one-parameter read, though brevity here edges into under-specification.

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?

An output schema exists so return values need not be explained, but with no annotations and 0% parameter coverage the definition leaves the agent without the one thing this hash-keyed lookup requires: how to obtain a valid audience_hash and what an invalid one produces. The tool is simple, yet the definition is thinner than that simplicity justifies.

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?

One parameter (audience_hash) at 0% schema description coverage. 'By hash' hints that the value is an opaque identifier but gives no format, source, or how to obtain a valid hash, so the description does not compensate 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?

States a specific verb ('Retrieve'), resource ('audience'), and scope ('single ... by hash'). 'Single' and 'by hash' implicitly separate it from list_audiences, though the other siblings sharing the audience prefix (get_audience_highlights, get_audience_patterns) are not addressed.

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 when-to-use guidance, no prerequisites, and no mention of alternatives such as list_audiences or the more specific get_audience_patterns/highlights. It offers a clear context but explicitly names no sister tool and no exclusion conditions.

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 the full behavioral burden, and it discloses almost nothing: no read-only confirmation, no mention of what a 'highlight' contains, no pagination or volume expectations. The only behavioral claim is the brand_hash prerequisite, which is already in structured data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded and free of padding, which is good. However, the second sentence duplicates the schema's required-parameter declaration rather than earning its place with new information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be described, but for a tool with two opaque hash parameters and zero annotations, the definition should explain what a highlight is and how this result differs from get_audience or get_audience_patterns. That context is entirely absent.

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 there are two required hash parameters. The description names only brand_hash (redundantly with the required list) and says nothing about audience_hash, nor about the format or relationship between the two hashes. It fails to compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description restates the tool name ('audience highlights') with a modifier ('brand-specific') and never supplies a verb or scope. It gives no way to tell it apart from get_audience or get_audience_patterns, which are its closest siblings. This is effectively a tautology with a hint of extra meaning.

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?

'Requires brand_hash' states a prerequisite that the schema's required array already enforces, not a usage condition. There is no indication of when to choose this tool over get_audience, get_audience_patterns, or list_brand_audiences. No when-to-use or when-not-to-use guidance is present.

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 the full behavioral burden. It says nothing about what 'pattern analysis' returns, how results are aggregated, permissions needed, or what the optional flags change — a significant gap for a 6-parameter analytical 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?

It is short and front-loads the core action, but the enumerated pattern_type list duplicates the schema verbatim and the trailing parameter list adds no explanatory value. Efficient in size, weak in information density.

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 annotations, low schema coverage, and an output schema that covers return values, the description still fails to explain what the optional filters do or how pattern analysis should be interpreted — substantial gaps remain for an analytical tool.

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 only 17%, so the description should compensate. It names the optional parameters (upload_timeframe, more_than_one_video, show_other_options, sort) but gives no meaning or value semantics for any of them, and the pattern_type enum values it lists merely duplicate 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 ('Get pattern analysis') and resource ('an audience'), which is clearer than the sibling get_audience. However, it does not distinguish itself from get_audience_highlights or explain how 'pattern analysis' differs from a plain audience fetch, leaving some ambiguity among siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus get_audience, get_audience_highlights, or list_audiences. It only notes that pattern_type is required, with no conditions, prerequisites, or exclusions provided.

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 the full behavioral burden. It does not state whether the operation is read-only, what happens on a missing/invalid hash (error vs null), or any auth requirements. These gaps leave an agent guessing about failure 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?

A single front-loaded sentence with zero waste. The verb and resource appear immediately, and the qualifier 'by hash' is correctly placed.

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?

An output schema exists, so return values need not be described. The tool is a simple one-param retrieval, but with no annotations the description leaves the behavioral profile (read-only nature, error handling) implicit, so it is only minimally 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 description coverage is 0%, so the schema documents only the parameter name and type. The description says 'by hash', which adds the minimal semantic that brand_hash identifies the record, but no format, source, or example for the hash is given.

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 (Retrieve) and resource (a single brand), and by specifying 'single' and 'by hash' it distinguishes itself from the sibling list_brands which presumably lists all brands.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this versus list_brands or other retrieval tools. The 'by hash' phrasing implies you need a hash, but there is no statement of prerequisites or when an alternative is preferable.

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. 'Retrieve' implies a read, but the description gives no behavioral context: no auth requirements, error handling, or side effects. It does not contradict anything, but it leaves the full disclosure burden unmet.

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?

Single sentence, front-loaded, zero wasted words. Appropriate for a simple retrieval tool.

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?

An output schema exists, so return values need not be described. However, for a tool with no annotations and no schema descriptions, the description omits task context such as how to obtain the hash or what errors to expect, leaving it minimally 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 0% and the one parameter is only a string. 'By hash' echoes the parameter name (idea_hash) without explaining hash format, source, or constraints. Adds almost no meaning 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 (Retrieve), resource (idea), scope (single), and lookup key (by hash). Clearly distinguishes itself from list_ideas (multiple) and generate_idea (creation).

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?

Implies usage when an idea hash is known, but does not name alternatives or state when not to use it. No explicit routing to list_ideas or generate_idea.

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 the full burden. 'Retrieve' implies a read-only lookup, but it says nothing about what happens when the hash is unknown, whether results are cached, or any auth constraints.

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 with the resource and lookup key front-loaded. There is no waste, though it is arguably too terse for a tool with zero annotation and parameter coverage.

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?

An output schema exists, so return values need not be explained, and a one-parameter read tool is simple. Still, with no annotations and no parameter documentation, the missing behavior (failed lookup, auth) leaves a modest 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% for the single parameter, so the description must compensate. 'By hash' clarifies that script_hash is the lookup key, but adds essentially nothing about format, length, or validity beyond the parameter name itself.

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 ('Retrieve') and resource ('script') with scope 'single', which implicitly distinguishes it from list_scripts and generate_script. It does not explicitly name a sibling, but the singular framing is enough to route most agents.

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 indication of when to use this over list_scripts or generate_script, and no mention of preconditions such as having a valid hash on hand. The agent must infer usage entirely from the name.

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

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

No annotations are provided, so the description carries the full burden. It discloses one useful behavioral fact, that results are filtered by token visibility, but says nothing about pagination, ordering, result size, or what happens past the limit. That is thin for a list tool with zero annotation coverage.

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 short sentence with the scope constraint front-loaded and no filler. Appropriately sized, though its brevity here reflects under-specification rather than disciplined editing.

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 presence of an output schema means return values need not be described, and the token-visibility note covers auth scoping. However, for a paginated list tool with one fully undocumented parameter, the description leaves the agent short of what it needs 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?

Schema coverage is 0%, and the description never mentions the sole 'limit' parameter or its default of 50. Since the parameter is entirely undocumented in both structured and prose fields, the description fails to compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('List project audiences') and adds a meaningful scope qualifier ('visible to this API token'), which separates it from get_audience (single item) and list_brand_audiences (brand-scoped). It does not explicitly name a sibling, so it stops short of a 5.

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?

There is no guidance on when to use this versus get_audience, list_brand_audiences, or list_brands, and no mention of pagination or how to walk results. The agent must infer the selection conditions from the name alone.

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 the burden alone. It usefully discloses the non-obvious default that only high-fit audiences are returned unless include_low_fit=true, which is genuine behavioral value. However, it says nothing about pagination, auth requirements, or response shape, leaving significant gaps for an unannotated 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?

Two short sentences, front-loaded with the core action and followed by the behavior modifier that matters most for correct invocation. No 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?

An output schema exists so return values need no explanation, and the description covers the key filtering default. But with 0% param coverage across 3 parameters and no annotations, the undocumented limit parameter and absent sibling differentiation leave it only minimally 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 0%, so the description must compensate. It explains include_low_fit's meaning and default behavior and implies brand_hash's role, but leaves the limit parameter entirely undocumented and gives no format detail for brand_hash. Partial compensation only.

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 (list audiences) scoped to a brand, plus the distinctive output trait (fit scores). It is distinguishable from the sibling list_audiences by the brand scoping and fit-score emphasis, but the description never explicitly names that sibling to sharpen the contrast.

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 sentence implies usage (get audiences evaluated for a brand) and discloses the default filtering behavior, but gives no explicit when-to-use versus list_audiences or get_audience, and no prerequisites. Usage is inferable rather than stated.

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 the full burden, and it does disclose one useful behavioral trait: results are scoped to what the API token can see, which implies permission-based filtering. It says nothing about pagination, result ordering, or the default/maximum page size for the limit parameter.

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 tight sentence with zero filler, but it is arguably too terse for a listing tool that has an undocumented pagination parameter.

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?

An output schema exists, so return values need not be explained, and the token-scoping sentence covers the auth aspect. Still missing is any pagination guidance for the limit parameter, which is the one control an agent must understand to call this 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 0%, so the single 'limit' parameter (default 50) is undocumented everywhere. The description adds no meaning about what the limit controls, acceptable ranges, or how to page through results, leaving the agent to guess.

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 ('List brands') with an explicit scope ('visible to this API token'), which cleanly separates it from the singular sibling get_brand. It does not, however, differentiate itself from the other list_* siblings beyond the resource 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?

There is no guidance on when to use this versus get_brand or list_brand_audiences, and no mention of prerequisites or when-not-to-use. The agent must infer the routing from the resource name alone.

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 the full disclosure burden. It does disclose the required parameter prerequisite, and listing is inherently a safe read, but it says nothing about ordering, pagination behavior, or what happens with the default limit of 50.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the action and immediately followed by the prerequisite. Nothing is wasted, though 'Requires brand_hash' partially repeats the schema's required field.

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 list tool with an output schema, the description covers the core operation and its prerequisite. It falls short on pagination/limit behavior and on distinguishing itself from the many sibling list/get tools.

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 schema documents names/types only. The description names brand_hash as required (matching the schema) but says nothing about the 'limit' parameter's meaning or default, leaving half the parameters without semantic value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('List ideas') and scopes it to a brand, which is enough for an agent to recognize it as the collection counterpart to get_idea. It does not name siblings or explain how it differs from get_idea/list_scripts beyond the obvious verb difference.

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?

There is no when-to-use guidance, no mention of alternatives (e.g., get_idea for a single idea, generate_idea for creation), and no context on when a brand-scoped listing is appropriate versus other listing tools. Only the hard prerequisite is stated.

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 the full burden of behavioral disclosure. It notes the filtering requirement but says nothing about pagination behavior, ordering, result size, or what a call without a filter would do, leaving significant behavioral gaps for a list operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the core action and then the requirement, with no filler. It is efficient, though the extreme brevity leaves useful detail unstated rather than trimmed as waste.

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?

An output schema exists so return values need not be described, but for a 3-parameter list tool with 0% schema coverage and no annotations, the description is too thin: no mention of limit/pagination, default result size, or behavior when both hashes are supplied.

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 does clarify that brand_hash and idea_hash act as filters and that one of them is needed, but it omits the limit parameter entirely, leaving one of three parameters undocumented in both schema and text.

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 clear verb+resource ('List scripts'), which an agent can distinguish from get_script and generate_script in the sibling set. It falls short of a 5 only because it doesn't further scope what is listed or how it differs from other list-style tools.

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 gives one precondition ('Requires brand_hash and/or idea_hash'), which is useful routing context, but offers no explicit when-not guidance or named alternatives. Usage is implied rather than fully specified.

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