openai-sora

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

With no annotations provided, the description carries the full burden of behavioral disclosure, yet it only reveals cost (1 credit/call) and app lineage. It is silent on response shape, pagination semantics beyond the schema's own last_id note, ordering, filtering side-effects, or error/rate 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 tight, front-loaded clauses with no filler words. Every element serves a purpose (identity, context, cost). It is brief to a fault, but for sheer economy of words it earns a high mark.

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 3-optional-param list endpoint with full schema coverage, the minimalism is partly forgivable, but given the absence of annotations, output schema, and sibling differentiation, the description leans on the agent to infer too much. It's adequate, not helpful.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with decent per-parameter descriptions (e.g., the last_id cursor pattern and the 'don't send to get all' note for task_type_filters), so the baseline 3 holds. The description itself adds no parameter insight, but none is strictly needed.

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 name and title convey it retrieves the v1 home feed, and the description adds a mildly useful 'Old Sora App' contextual note. However, it never differentiates itself from its near-twin siblings get_v1_feed_top, get_v1_feed_images, and get_v1_feed_videos, so the agent must guess what makes 'home' distinct.

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 is given. The description never explains when to choose this over the other v1 feed variants or the get_v2_feed family. Only implicit signal is the 1-credit cost, which doesn't aid tool selection.

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 must disclose behavioral traits. It mentions billing (1 credit per call) but does not state that this is a read-only operation, whether pagination is involved (though the 'after' param hints at it), or any other side effects. The bare description leaves safety and behavior entirely opaque.

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?

While very short (one sentence), it conveys almost no useful information beyond identifying the endpoint group. The line 'Group: v1 Endpoint (Old Sora App)' is borderline redundant with the title. It is concise but not effective, as it omits purpose and usage details.

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 feed tool with only 2 optional parameters and no output schema, the description should explain what the tool returns and any operational constraints. It only mentions billing and the group, leaving the agent to guess the response structure and behavior. Given the lack of annotations and output schema, this is insufficient.

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 input schema already provides full descriptions for both parameters (after and limit) with 100% coverage. The tool description adds no additional parameter semantics. Baseline 3 is appropriate since the schema handles 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?

The description states 'Images Feed' which implies retrieving a feed of images, distinguishing it from sibling feeds like videos and home/top. However, it lacks a clear verb (e.g., 'Retrieve') and provides no detail on what the resource is beyond the name. It is minimally clear but not fully descriptive.

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 any selection criteria, constraints, or comparisons to sibling tools such as get_v1_feed_videos or get_v2_feed.

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 only adds billing cost and the legacy v1 context; it does not describe what the response contains, pagination behavior, authentication needs, or any side effects. This is insufficient for a tool with no annotation support.

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 brief and does not waste words, but it partially restates the title with 'v1 / Top Feed Group' and the 'v1 Endpoint' label. It is compact rather than substantive, so it earns a mid score for conciseness.

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?

There is no output schema and no annotations, so the description should explain what the endpoint returns and how to use it effectively. It does not mention the meaning of 'Top Feed,' response shape, or filter semantics beyond the schema, leaving the tool under-specified for an agent.

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 input schema already covers 100% of parameters with individual descriptions for after, limit, time_range, and task_type_filters. The prose description adds nothing parameter-specific, but high schema coverage makes a baseline of 3 appropriate.

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

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

The description identifies the resource as 'v1 / Top Feed' and labels it as a v1 endpoint, but it never states what the tool actually does beyond the name 'get_v1_feed_top.' It vaguely distinguishes v1 from v2 and mentions 'Old Sora App,' but does not differentiate it from sibling tools like get_v1_feed_home or get_v1_feed_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?

There is no explicit guidance on when to use this tool versus alternatives. The only contextual hint is 'Old Sora App,' which might imply legacy use, but the description never states scenarios, exclusions, or which sibling endpoint to choose instead.

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 provided, the description carries the full burden of behavioral disclosure. It says nothing about whether the operation is read-only, what it returns, pagination, authentication, or side effects. The only added detail is billing per call, which is not behavioral tool 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 extremely short, but this is under-specification rather than effective conciseness. It wastes the opportunity to convey any useful information, making it unhelpful despite its brevity.

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 has no annotations, no output schema, and the description provides only a label and billing info, it is completely inadequate. With many sibling feed tools, differentiation is essential and entirely 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 input schema provides complete descriptions for both parameters ('after' and 'limit') with 100% coverage, so the schema alone is sufficient. The description adds no additional meaning beyond the schema, so baseline 3 is appropriate.

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

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

The description is essentially a duplicate of the tool name and title: 'v1 / Videos Feed'. It lacks a verb or specific action, and doesn't distinguish this from sibling tools like get_v1_feed_images or get_v1_feed_top. It is tautological.

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 about when to use this tool versus alternatives. The description only mentions billing, which offers no context for selection among the many feed 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?

No annotations exist, so the description carries the full burden. It discloses billing per call (a minor operational detail) but says nothing about side effects, return behavior, rate limits, or whether it's read-only. With no annotations and a generic endpoint label, the agent has no idea what this tool does behaviorally beyond the billing hint.

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?

While very short, it's under-specified rather than concise. The content is mostly metadata (group, endpoint, billing) rather than actionable guidance. It fails to earn its place by omitting essential purpose and usage information. No front-loading of critical details.

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 single parameter locked to a specific generation_id, no output schema, and a vague description, the agent cannot infer what the call returns, what 'Post Details' means, or how it relates to siblings. The description is far from complete for a two-line call 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?

The input schema has one parameter (generation_id) with a description ('Allowed Generation ID'), giving 100% schema coverage. However, the tool description adds no additional semantics about how to use the parameter or what it represents. Per rubric, baseline 3 is appropriate since schema covers it well, though the parameter description itself is ambiguous ('Allowed' is unclear).

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 is 'v1 / Post Details Group: v1 Endpoint (Old Sora App). Billing per call: 1 Credits.' It essentially restates the tool name without a clear verb+resource action. It doesn't explicitly say 'retrieve details for a specific generation/post' or distinguish from sibling 'get_v2_post_details_and_replies'. Purpose is vague and under-specified.

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 siblings. There's no mention of prerequisites, when to call it, or when not to. The description provides zero usage context beyond a billing note.

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?

There are no annotations, so the description must disclose behavioral context, and it only adds billing cost and legacy grouping. It does not disclose whether this is read-only, whether authentication is needed, what data it returns, or any limits/errors—leaving a significant 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 compact and front-loaded, with no unnecessary prose. The only minor issue is that the opening phrase essentially repeats the tool name and title, but overall the content is efficiently organized.

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

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

With no output schema and no annotations, the description leaves important gaps about what 'Profile Details' actually contains and what the user_id parameter is used for in practice. The billing/cost note is useful, but the description is too sparse to function as a standalone usage guide.

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 input schema covers the single parameter 'user_id' with a description ('Allowed User ID'), so schema coverage is 100%. The description adds no extra parameter semantics, which is acceptable at the baseline since the schema already handles the one parameter.

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 is mostly a restatement of the name: 'v1 / Profile Details' and 'Group: v1 Endpoint' do not clearly state an action like retrieves, lists, or returns. It adds context about the old Sora app and billing but does not distinguish the tool's core function beyond what the name already implies.

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 about when to use this tool versus alternatives such as get_v2_profile_details or get_v1_post_details. The description only mentions it is the v1/old Sora endpoint and states the billing cost, which implies legacy usage but does not explicitly state when to choose this tool.

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 must carry the full burden of behavioral disclosure. It only mentions billing and provides no information about side effects, read-only nature, pagination, rate limits, or return format. The tool's function is entirely opaque.

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 only one sentence but is under-specified, not concise. It repeats the tool's category and mentions billing, which is not a functional description. The structure provides no useful information for an agent.

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 search tool with four optional parameters and no output schema, the description provides almost no context. It fails to explain what content is searched, how pagination works (beyond schema hints), how similar_to is used, or how results are returned. The tool's role is not adequately contextualized.

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 input schema has 100% coverage with descriptions for all four parameters (after, query, user_id, similar_to), so the description does not need to add parameter details. The description adds no parameter-specific meaning beyond the schema, but the baseline of 3 applies due to high schema 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?

The description 'v1 / Search Group: v1 Endpoint (Old Sora App). Billing per call: 1 Credits.' merely restates the tool's name and adds billing info, without stating a specific action or what is searched. It is a tautology that doesn't distinguish from sibling search tools like get_v2_search.

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 tool versus alternatives. The description only mentions billing and identifies it as an old Sora app endpoint, but does not explain when to prefer it over v2 search or feed tools. No exclusions or alternatives are 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?

The description mentions billing ('1 Credits'), which is a behavioral trait, but it does not state whether the operation is read-only, its side effects, or any rate limits. The absence of annotations places the onus on the description, which is only partially transparent.

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 brief but not well-structured—'v2 / Feed Group: v2 / Explore' is a header-like string that adds little value. The billing line is useful but the overall structure feels like a placeholder.

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?

There is no output schema and the description does not indicate what the tool returns or how the response is structured. It lacks sufficient context to understand the tool's full scope, especially in comparison to the sibling feed 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?

The schema already provides full descriptions for all three parameters, including the meaning of 'cut' and the cursor usage. The tool description adds no additional insight, so the parameter semantics are adequately handled by the schema alone.

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 'v2 / Feed Group: v2 / Explore' is cryptic and does not clearly state what the tool does. It fails to describe an action (e.g., retrieve or list) and merely echoes the tool 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 tool versus its siblings (e.g., get_v1_feed_home). No mention of typical use cases or scenarios where this feed is preferred.

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. The description only mentions billing ('1 Credits') and group membership, but does not mention that this is a read-only operation, how pagination works (beyond the existence of cursor), or any side effects. It adds negligible behavioral 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 extremely short (one sentence), but it is not appropriately concise—it under-specifies essential information. It frontloads billing/grouping details rather than functional utility, so the brevity undermines clarity rather than aiding it.

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

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

With no output schema and no annotations, the description must provide broader context about the tool's behavior, return values, and typical usage. It does none of this. Even though parameters are documented in the schema, the description is incomplete for a tool with four parameters and no structured output information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds no parameter-specific information; it leaves all semantic detail to the schema, which already documents each parameter with examples and descriptions. The description does not compensate or enrich the schema meaning.

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 is essentially a label 'v2 / Post Details & Replies' that restates the tool's name without explaining what the tool actually does. It lacks a specific verb+resource description and does not clarify scope or differentiate it from sibling tools like get_v1_post_details or get_v2_feed.

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 tool versus alternatives. Sibling tools include similar post-detail tools, but the description offers no context, exclusions, or recommended scenarios, leaving the agent to infer usage 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?

No annotations exist, so the description must carry behavioral context. It discloses only a billing and grouping label, not whether the operation is read-only, what it returns, pagination behavior, authentication requirements, or side effects. This is a major transparency gap for a feed 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 text is extremely short but mostly repeats the title and adds non-functional metadata. 'Billing per call: 1 Credits' is useful, but the rest is structural labeling. The body under-specifies the tool rather than being efficiently informative.

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 no output schema, no annotations, and a simple two-parameter schema, the description should explain what a 'post remix feed' is, what kind of data is returned, and how it relates to sibling feed tools. It does none of this, leaving important missing context for an AI agent.

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 input schema covers 100% of the parameters with meaningful descriptions: cursor explains how to get additional results, and post_id identifies the target post. The description itself adds no parameter details, but the schema already provides sufficient semantic coverage, so the baseline 3 is appropriate.

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

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

The description is essentially a restatement of the title: 'v2 / Post Remix Feed Group: v2 / Post.' It provides no verb, no operation explanation, and no scope beyond the already-visible name. It does not meaningfully clarify what the tool actually gets or does.

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

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

No guidance is given for when to use this tool versus sibling tools such as get_v2_feed or get_v2_post_details_and_replies. The description only mentions billing and grouping, so the agent is left without context for selecting between feeds or understanding expected use cases.

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?

There are no annotations, so the description must carry the full burden of behavioral disclosure. It only mentions billing and grouping, but does not disclose what data is returned, whether the operation is read-only, pagination behavior, or any side effects. This is transparent about nothing except cost.

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 short but under-specified; this is not effective conciseness because it omits the core purpose. It front-loads irrelevant administrative details (group and billing) rather than any functional explanation. The content is too sparse to be considered well-structured.

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

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

With no annotations, no output schema, and only a three-word title-like description, the tool is completely underdocumented. An agent cannot understand what 'cameos' means, what the response will contain, or how to use the parameters effectively. The description is inadequate even for a simple read 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 100%, so the input schema already provides baseline meaning for all three parameters: limit, cursor, and user_id. The tool description adds no parameter-level meaning beyond this, and the schema descriptions are minimal but adequate.

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 is 'v2 / Profile Cameos Group: v2 / Profile. Billing per call: 1 Credits.' It contains no verb or resource/action statement, merely restating the title and group. It does not say what 'cameos' are, what the tool does, or how it differs from sibling profile tools like get_v2_profile_feed or get_v2_profile_details.

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 instead of any sibling tool. There is no stated context, prerequisites, or alternatives, leaving the agent with no basis for selection among the many get_v2_profile_* 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?

No annotations are provided, so the description carries the full burden for behavioral disclosure. The only behavioral fact disclosed is 'Billing per call: 1 Credits,' which is useful but insufficient. The description does not explicitly say this is a read operation, mention authentication needs, describe output shape, or note any limitations.

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 short but under-specified. It repeats the title and group rather than providing meaningful substance. 'Billing per call' earns its place, but the rest is redundant filler, so the structure does not satisfy the intent of concise, useful documentation.

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 has low complexity (one parameter) and full schema coverage, but no annotations and no output schema. The description still needs to state what details are returned and how this differs from existing sibling tools. With only a billing note and a tautological title, the context is incomplete for informed selection and 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 100%: the single 'username' parameter has a description and example. The tool description adds nothing about the parameter beyond the schema, but because the schema already fully documents it, the baseline of 3 is appropriate.

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

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

The description merely restates the tool name and title ('v2 / Profile Details') and adds a grouping label. It never states what the tool actually does with a verb and resource. This is a tautology, not a purpose statement, and it does not differentiate from get_v1_profile_details or get_v2_profile_feed.

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 about when to use this tool versus siblings like get_v1_profile_details or get_v2_profile_feed. The 'Group: v2 / Profile' label gives a category but no usage context, prerequisites, or exclusions. This is a clear absence of usage 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?

No annotations are provided, so the description must disclose side effects, safety, and behavior. It does not mention any behavioral aspects such as read-only nature, pagination handling, authentication needs, rate limits, or what happens with missing parameters. The only 'behavioral' note is 'Billing per call: 1 Credits', which is trivial and does not aid safe invocation.

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

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

The description is extremely short, but conciseness is not the issue; under-specification is. It contains two phrases that are largely redundant with the title and adds only billing information. There is no front-loaded value or structured content, making it closer to the 'Process' example of under-specification rather than efficient brevity.

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 has 3 parameters, no output schema, no annotations, and a trivial description, the context is wholly incomplete. It does not explain what the feed contains, how pagination works (though cursor is mentioned in schema), how limit affects results, or what user_id refers to. An agent cannot infer the tool's full capabilities or expected response without external knowledge.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds no extra meaning to the parameters (limit, cursor, user_id) beyond what the schema already provides. Since the schema is complete, the description does not diminish comprehension, but it also does not augment the parameter semantics with context like typical ranges or relationships.

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 essentially repeats the title and group, and does not explicitly state a verb or action like 'retrieve' or 'list'. It hints at content ('Posts') but fails to clarify what the tool does or how it differs from sibling feed tools such as get_v2_feed or get_v1_feed_home. The purpose is only implied by the name, not explained.

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 tool versus alternatives. The description only includes group and billing info, with no mention of use cases, prerequisites, or exclusions. Sibling tools like get_v2_profile_cameos or get_v2_feed are not referenced, making it impossible for an agent to decide when to invoke this tool.

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 does not disclose any behavioral traits such as pagination behavior, rate limits, or whether it is a read-only operation. The only extra info is billing cost, which is not behavioral transparency.

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 short (one sentence), which is concise, but it is under-specified. It repeats the title and adds a billing note, which is not useful for tool selection. It is not front-loaded with functional 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 the tool has 3 parameters, no output schema, and no annotations, the description is inadequate. It does not explain what the tool returns, how pagination works (though cursor is mentioned in schema), or any prerequisites. The billing note is irrelevant to functionality.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all three parameters. The description adds no additional meaning beyond what the schema provides. Baseline 3 is appropriate since the schema does the heavy lifting.

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 is essentially a title and billing note, not a functional description. It says 'v2 / Profile Followers' which indicates the resource (profile followers) but lacks a verb like 'get' or 'list'. It does not distinguish from sibling tools like get_v2_profile_following or get_v2_profile_feed, though the name itself is somewhat 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?

No guidance on when to use this tool versus alternatives. The description only mentions billing per call, which is not usage guidance. Sibling tools exist for similar profile-related operations, but no differentiation is 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?

With no annotations provided, the description carries the full burden, yet it discloses nothing about behavior, auth requirements, rate limits, or what the endpoint returns. The only transparency is billing cost and group membership.

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 short but not usefully so — it's under-specified rather than concisely informative. The only real content is billing information, which is out of place as a primary purpose statement.

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 and no output schema, the critical semantics (e.g., that this returns users whom a given profile follows) are entirely missing. Sibling tool names suggest a followers/following distinction that is never clarified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with descriptions for all three parameters, including a helpful cursor explanation and a user_id example. Per the rubric, with high coverage the baseline is 3, and the description adds nothing beyond what the schema already documents.

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 'v2 / Profile Following Group: v2 / Profile' merely restates the tool's title and group membership without stating a function. No action verb or resource is mentioned, only the tool name 'get_' hints at retrieval, and the billing note is operational, not functional.

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 its many siblings. There's no mention of when to prefer this over get_v2_profile_followers, get_v2_profile_feed, or other v2 profile tools, and no exclusions or prerequisites.

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 transparency burden but discloses nothing about behavior—no return format, no result semantics, no side effects. The 'Billing per call: 1 Credits' note is the sole behavioral detail, which is thin. The tool's behavior (what does it actually search? users only? posts?) is completely opaque.

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?

At 13 words, the description is certainly short and front-loaded with the identifier. However, the brevity reads as under-specification rather than deliberate concision—there simply isn't substantial content to evaluate for quality.

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 0 required params, no output schema, and no behavioral annotations, the description is the only place for an agent to understand tool limits, return shape, or relationship to get_v1_search/get_v2_feed. It does not clarify what 'search' returns, how it differs from v1, or what 'credits' mean functionally. This is inadequate for an agent to confidently select this tool over its sixteeen siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% — both 'limit' ('Result limit') and 'username' ('Search query for users') are documented. The description itself adds no parameter meaning, but since schema coverage is high, the baseline score of 3 applies.

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 'v2 / Search' restates the tool name without adding meaning—it's essentially a tautology. The 'Group: v2 / Explore' categorization and billing note add no clarity about what the tool does. Purpose must be inferred from the name and the username parameter, not from the description itself.

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 tool versus alternatives. Notably, the sibling list includes get_v1_search and get_v2_feed, creating obvious ambiguity about version differences, yet the description offers no differentiators or usage context.

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