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

Beyond annotations (which only indicate readOnly=false etc.), the description discloses key behavior: asynchronous execution, result structure, and cost implications ('preview the cost before spending credits', 'billed at 50%'). This adds valuable context annotations do not provide.

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 dense paragraph, but every sentence serves a purpose: purpose, input, async behavior, result, validation, and batch alternative. It is appropriately sized for a complex tool and front-loaded with the core action.

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

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

Given the tool's complexity (async, cost, validation, batch), the description covers all major workflow aspects: how to use, what to expect, prerequisites, and alternatives. Output schema exists, so not explaining return values is acceptable; the description goes beyond by summarizing result fields anyway.

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 parameters are fully documented in the schema. The description reiterates video_id and prompt examples but adds no new meaning beyond schema. Baseline 3 is appropriate; no extra semantic value is added.

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

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

The description opens with 'Ask a question about a video (POST /v1/analyses)', clearly stating the verb and resource. It distinguishes the tool from siblings by noting async behavior ('use wait_for_analysis to block'), validation ('call validate_analysis first'), and batch alternative ('use create_analysis_batch').

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?

Explicit guidance is given: when to use this tool (single analysis), when to use alternatives (batch for 2–10 prompts, wait_for_analysis to block), and a recommended pre-step (validate_analysis). This fully clarifies usage vs. siblings and constraints.

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

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

The description discloses important behavioral details beyond annotations: the first prompt is full price and each additional is 50% off, the result includes a pricing summary, and each analysis id must be polled individually. Since annotations only provide generic flags (readOnlyHint=false, destructiveHint=false), the description carries the transparency burden well. A slight gap is that it doesn't explicitly mention a credit deduction or that this creates persistent resources, but the pricing information strongly implies it.

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

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

Three sentences, each earning its place: main action, pricing incentive, and follow-up/alternative guidance. The most important info is front-loaded, and no filler words exist.

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 creation call, pricing, return structure, how to retrieve results, and when to use an alternative. With an output schema present, the tool is fully specified for an agent to invoke correctly without guesswork.

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

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

Input schema covers 100% of parameter descriptions, so the baseline is 3. The description reinforces the prompts parameter with the pricing tier (first full, additional 50%) which is already stated in the schema. It does not add new meaning for video_id, model, or metadata beyond what the schema provides.

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

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

The description opens with a specific verb and resource: "Run 2–10 prompts against the SAME video in one call" and explicitly names the endpoint POST /v1/analyses/batch. It clearly differentiates from siblings by emphasizing batch execution on the same video, which is the unique capability versus create_analysis or validate_analysis.

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

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

The description explicitly states when to use this tool: "always cheaper than separate create_analysis calls for multi-question workloads," and tells the user to use validate_analysis for pre-checking assessability, and to poll with get_analysis or wait_for_analysis for individual results. It clearly contrasts with alternatives and gives direct guidance.

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

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

Beyond annotations, the description discloses key behaviors: the video is fetched asynchronously, status transitions from 'processing' to 'ready', supports specific formats (mp4/quicktime) and size limits (2 GiB), and returns a video id. This adds significant operational context not evident from 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?

Three sentences, each fact-dense: purpose/endpoint, async behavior, and supported constraints/return. No redundancy or filler. Every sentence earns its place.

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 output schema and annotations, the description covers all essential aspects: what it does, how it behaves (async), constraints, and return value. It is sufficiently complete for an agent to decide when and how to invoke this 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 coverage is 100%, so parameters are already described. The tool description adds extra constraints (format and max size) on the URL parameter, going beyond the schema's description. This adds meaningful value despite 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 uses a specific verb 'Register' and clearly names the resource ('a video from a public https URL') and mode ('URL-ingest'). It differentiates from sibling tools like create_analysis by specifying it creates a video resource rather than an analysis.

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

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

The description provides clear context: it is for URL-based video ingestion for analysis, and notes asynchronous fetching. It does not explicitly mention alternatives or when not to use, but the context is unambiguous and sufficient for 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description goes far beyond by detailing the live progress fields, the full result object with all possible indeterminate_reason values, and the immutable usage snapshot. This adds significant behavioral context about what to expect in various states.

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 long but every sentence provides essential information about the response format and edge cases. It is front-loaded with the core action and then systematically enumerates fields and their meanings, with no filler or 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?

For a single-parameter fetch tool with complex response semantics, the description is exceptionally complete. It covers the running state, completed result fields, the usage snapshot, and explains each indeterminate_reason, leaving no major gaps for an agent to invoke or interpret the result.

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 a clear parameter description ('The analysis id (an_…).'). The tool description does not add extra meaning about the parameter itself, so the baseline of 3 is appropriate.

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

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

The description starts with 'Fetch an analysis by id (GET /v1/analyses/{id})', a specific verb+resource that exactly matches the tool name and clearly distinguishes it from siblings like wait_for_analysis or create_analysis. It also provides a detailed preview of the response, reinforcing what the tool does.

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

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

The description implies usage by explaining the behavior during running and completed states, but it does not explicitly state when to use get_analysis instead of sibling tools like wait_for_analysis. There are no exclusions or alternative recommendations, so it stops at implied context.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds valuable behavioral context: it identifies balance_seconds as the authoritative balance, explains the transaction list is paginated, and notes that each debit carries source_id/source_type. This goes beyond the annotation 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 three sentences, front-loaded with the main purpose, followed by return structure and use cases. Every sentence is informative, with no redundancy. It is both concise and well-structured.

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

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

Given the output schema exists and the tool is a straightforward read-only query, the description is complete. It explains the return fields, the pagination behavior, and the practical use cases. There is no missing context that would hinder the agent's ability to use the tool correctly.

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

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

Schema coverage is 100%, with both parameters (limit and before) having descriptions. The description does not add any additional parameter-level detail beyond what the schema already provides, so the baseline score 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 starts with a specific verb and resource: 'Get the credit balance and transaction ledger for this API key'. It clearly distinguishes this from siblings like get_usage by focusing on credits, balance, and transaction ledger, and even specifies the endpoint. This is a model of purpose clarity.

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 explicit use cases: 'audit what each analysis cost, check the balance before a batch job, or diagnose an insufficient_credits error.' This gives the agent clear when-to-use guidance. However, it does not mention any alternatives or exclusions (e.g., when NOT to use it), so it falls just short of a 5.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds important behavior: the tool returns a static fixture, does not consume quota, and test-mode keys yield deterministic canned results. These details go beyond annotations and help the agent understand the tool's side-effect-free 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 two sentences, with the core purpose stated upfront. Every clause provides relevant information: endpoint, content, purpose, quota savings, and test-mode behavior. No fluff or 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?

For a parameterless tool with an output schema and comprehensive annotations, the description covers all needed context: what it returns, why to use it, and how test-mode affects results. There are no gaps in understanding when or 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 tool has zero parameters, and the schema reflects this with an empty properties object. The description need not explain parameters. Since there are no params, the baseline of 4 is appropriate; the description doesn't need to compensate for any missing parameter info.

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 'Get the stable test fixture (GET /v1/test-fixture)' with a specific verb and resource, and enumerates the exact contents: 'a video URL + prompt + expected answer'. It distinguishes itself from sibling tools by focusing on testing/verification use case, making it unmistakable.

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

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

The description explains when to use this tool: 'for verifying an integration end-to-end without burning quota', and adds a conditional about test-mode keys. It implies this is for testing scenarios, but does not explicitly mention alternatives or when not to use it. Since siblings are unrelated, this is clear enough.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering safety. The description adds useful context: it operates on the 'current API key' and includes the REST endpoint, plus the specific error scenario. This goes beyond the annotations without contradicting them.

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, front-loaded with the main function, then usage context and alternative. Every word earns its place; 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, a read-only annotation, and an output schema present, the description fully covers what the tool does, when to use it, and its scope. The mention of the endpoint and error scenario adds complete operational context.

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

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

The tool has zero parameters, so the baseline is 4. The description doesn't need to elaborate on parameters, and the schema trivially covers 100% of them.

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 'Get credit balance and period usage meters for the current API key' with a specific verb and resource. It also names the sibling tool get_credits, distinguishing this tool as the balance/usage meter versus the per-analysis ledger.

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 says 'Use this after an insufficient_credits error to report the balance' and provides a direct alternative: 'For the per-analysis transaction ledger... use get_credits instead.' This gives both when-to-use and when-not-to-use guidance.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, establishing a safe read operation. The description adds behavioral context by specifying the HTTP method, the status values returned, and the default:true selection rule, going beyond the structured metadata without 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?

Two sentences with no filler. The first states purpose and scope, the second offers a practical selection rule. Both are essential and immediately understandable, making the description highly efficient.

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

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

For a parameterless listing tool with an output schema and read-only annotations, the description adequately covers what the tool returns and provides a default model heuristic. Nothing critical is missing given the context signals and sibling tool set.

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 has zero parameters, so there is no parameter ambiguity. The schema is trivially fully covered, and the description adds no parameter details because none are needed. Baseline 4 for a no-parameter tool 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 explicitly states the tool lists available analysis models, specifies the REST endpoint (GET /v1/models), and enumerates the returned metadata (status, capabilities). This clearly distinguishes it from sibling tools like get_analysis or create_analysis.

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

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

The description implies when to use the tool (when needing to see available models) and provides a concrete guideline to prefer the default:true model unless there's a reason not to. It does not explicitly contrast with alternatives or state exclusions, so it falls short of a 5.

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

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

Beyond the readOnlyHint annotation, the description discloses key behaviors: no analysis creation or credit spending, return of analysis_preview, interpretation of 'assessable: false', and null handling for estimated_seconds/cost when video duration is unknown. 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?

The description is brief but information-dense: two compound sentences lead with the core purpose and then efficiently cover return fields and usage recommendation. Every clause adds meaningful detail without redundancy.

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

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

With output schema present and annotations covering safety, the description adds the missing context: when to use it, what triggers null values, and how to interpret assessable. It is complete for an AI agent to select and invoke the tool correctly.

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

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

Schema covers all three parameters (100% coverage), so baseline is 3. The description adds value by explaining that 'assessable: false' implies the prompt may need rephrasing as a yes/no or count question, and clarifies when cost/seconds are null—semantics beyond the raw schema.

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

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

The description clearly states the tool's purpose: 'Dry-run a prompt WITHOUT creating an analysis or spending credits.' It identifies the exact resource (analyses) and differentiates from siblings like create_analysis by emphasizing the dry-run nature.

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

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

Explicitly recommends using this tool before create_analysis to 'catch unassessable prompts and preview cost.' This provides clear when-to-use guidance and names the primary alternative (create_analysis), making the usage context unambiguous.

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, destructiveHint=false, and openWorldHint=false, covering the safety profile. The description adds valuable behavioral context: it explicitly states the polling endpoint, the return object shape with retry semantics, timeout expiration behavior, and the default timeout value. This goes beyond the annotations and helps the agent understand the blocking/polling 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 compact and well-structured: the first sentence states the core purpose, the second describes the return shape, the third gives timeout context, and the fourth points to the sibling tool for result semantics. Every sentence earns its place with no redundancy or fluff, 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?

Given the tool's complexity (blocking, polling, timeout, retry) and the presence of an output schema, the description covers the key aspects: terminal states, return structure, timeout behavior, and a pointer to get_analysis for detailed field semantics. It does not detail the polling interval or cancellation options, but these are minor gaps given the output schema covers the return shape.

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 100% coverage with descriptions for both analysis_id and timeout_s, including min/max constraints. The description adds semantic value by explaining the default timeout (120s), the fact that test-mode analyses complete in seconds, and how the retry field behaves on timeout. This supplements the schema meaningfully.

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

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

The description opens with a specific verb and resource: 'Block until an analysis reaches a terminal state (completed | failed | canceled), polling GET /v1/analyses/{id}.' This clearly states the tool's function and scopes it to a polling, blocking behavior, distinguishing it from the sibling get_analysis which retrieves results without blocking.

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

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

The description provides clear usage context: it mentions the default timeout, that test-mode analyses complete in seconds, and that retry should be called again if the wait expires. It also points to get_analysis as the alternative for result field semantics after completion. It lacks an explicit 'when not to use' statement, but the context is sufficient.

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