speechmatics

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

Annotations already provide destructiveHint: true, but the description adds important context: the deletion is permanent and also removes the transcript. The force flag behavior is also disclosed, adding value beyond the annotation.

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 concise sentences, front-loaded with a warning emoji. Every word earns its place, covering permanence, the transcript, and the force flag 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?

For a simple 2-parameter destructive action with no output schema, the description is fully complete. It covers the core behavior, the force option, and even includes the API endpoint. No significant gaps exist.

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 reinforces the force parameter's meaning but does not add information beyond the schema. No additional parameter context is 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?

The description states a specific verb ('deletes') and resource ('job and its transcript'), and the permanence is emphasized. It clearly distinguishes itself from the sibling tools, which are all retrieval or creation operations.

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

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

The description explains the force parameter for deleting a running job, which is key usage context. It does not explicitly name alternatives or when-not-to-use, but the destructive nature and sibling tool set make the intended use clear.

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

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

Annotations already provide readOnlyHint=true, and the description adds the job status lifecycle and the expected polling behavior. It goes beyond the annotation by clarifying the statuses and the post-poll step, which is useful for the agent's decision-making.

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: the first front-loads the action and scope, the second gives essential workflow guidance and API path. Every word earns its place with no redundancy.

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

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

Given the simple one-parameter schema and no output schema, the description covers the purpose, statuses, and polling workflow adequately. The only minor gap is that it doesn't describe the response payload shape, but the instruction to fetch the transcript separately implies the job details are separate.

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% for the single parameter job_id, with the schema already stating 'The job id returned by speechmatics_transcribe_url.' The description adds no further parameter semantics, so 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 clearly states 'Get a single job's details and status' with enumerated statuses (running | done | rejected | deleted | expired), making the verb and resource explicit. It also distinguishes itself from sibling tools like list_jobs and get_transcript by focusing on a single job and its polling lifecycle.

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 usage guidance: 'Poll this until status is "done", then fetch the transcript.' This tells the agent when to use the tool and how it fits into the workflow. While it doesn't explicitly list exclusions or alternatives, the context is clear enough for correct selection among sibling 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?

With readOnlyHint=true already communicating the safety profile, the description adds the plain-text nature of the log and the exact Batch API endpoint, which helps the agent understand what to expect without contradicting 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?

Two sentences: the first states purpose and use case, the second provides the API reference. No wasted words, front-loaded with the essential 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?

For a single-parameter, read-only tool with no output schema, the description fully covers what the tool does, when to use it, and how to invoke it via the API path. Nothing essential is missing.

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

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

Schema coverage is 100% for the sole parameter job_id, so the schema already defines it. The description's endpoint path slightly reinforces that it is interpolated into the URL, but doesn't add substantive 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?

The description clearly identifies the action (Get) and resource (job's plain-text processing log), and adds the debugging context that distinguishes it from sibling tools like get_job and get_transcript.

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 explicitly states the tool is useful for debugging a rejected job, which conveys a clear use case. It doesn't name alternative tools or exclusions, but the context is sufficient for selecting it appropriately.

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 readOnlyHint annotation already signals safety, and the description adds meaningful behavior: the transcript is only available once the job is 'done', and it lists the available output formats (txt, srt, json-v2) with their intended uses. This goes beyond the annotation 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?

The description is a single, well-structured sentence that front-loads the main purpose and uses a compact pipe-separated format list. Every clause adds value (formats, status requirement, API path) with no redundancy or fluff.

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

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

For a simple read-only retrieval tool with two parameters and no output schema, the description covers the essentials: purpose, formats, prerequisite status, and API endpoint. The only minor omission is explicit error behavior, but the description is sufficient for an agent to invoke this tool correctly.

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

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

Schema description coverage is 100% with clear descriptions for both job_id and format, including the enum. The description adds marginal value by restating the default format and the meaning of json-v2, but this largely duplicates the schema. 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 clearly states the tool's purpose with a specific verb and resource: 'Get a completed job's transcript.' It distinguishes itself from siblings like get_job (job metadata) and get_job_log by focusing on the transcript output. The format list adds further specificity.

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 works only when the job status is 'done', which is a key prerequisite. It also implies this is the tool to use for transcript content, not job status or logs. However, it does not explicitly name alternatives or exclusions (e.g., 'use get_job for status').

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, so the read-only nature is known. The description goes beyond annotations by clarifying the data scope (account-level transcription minutes) and the temporal dimension (date range). It also introduces the Batch API endpoint, which indicates the underlying service context. This adds meaningful context beyond the annotation 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?

The description is two sentences, front-loaded with the primary purpose, and includes the API endpoint as supplementary info. There is no redundant phrasing or unnecessary detail. Every sentence contributes to understanding the tool's function and scope.

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 only two optional parameters and no output schema, the complexity is low. However, the description does not explain behavior when parameters are omitted (e.g., whether a default range applies) or describe the response format in any detail. These gaps, while not critical for simple usage stats, leave room for minor ambiguity in agent 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%, as both 'since' and 'until' parameters have descriptive strings. The description adds 'over a date range' which maps to these parameters, but does not provide additional syntax, defaults, or edge-case details. Since the schema carries the semantic load, the description adds limited value beyond the structured fields.

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

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

The description clearly states the verb 'Get' and the resource 'usage statistics (transcription minutes) for the account over a date range.' It distinguishes itself from sibling tools that operate on individual jobs (e.g., list_jobs, get_job) by focusing on account-level aggregation. The API endpoint is also specified, leaving no ambiguity about the tool's function.

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 context by specifying 'for the account over a date range,' but it does not explicitly state when to use this tool versus alternatives like list_jobs or get_transcript. There are no exclusionary statements or named alternatives, so the guidance is implied rather than direct.

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 adds useful behavioral details: results are most recent first, include status/data_name/duration, and reference the Batch API endpoint. It doesn't cover pagination or rate limits, but the annotation lowers the burden.

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 deliver the essential information: what is listed, ordering, returned fields, and API endpoint. Every phrase adds value with no redundancy.

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

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

For a simple list tool with complete parameter schemas and read-only annotations, the description provides sufficient context (ordering, fields, endpoint). It omits only optional details like default limit or pagination strategy, but these are covered by the schema's parameter descriptions.

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% and all three parameters have descriptive text, so the description does not need to explain them. It adds no additional parameter semantics beyond the schema's definitions.

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 and resource ('List transcription jobs') with ordering and returned fields, clearly distinguishing it from sibling tools like get_job (singular) and delete_job. The scope is unambiguous.

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

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

The description states what it does ('List transcription jobs') but does not explicitly compare to alternatives such as get_job for a single job or mention when not to use it. The usage is implied rather than prescribed.

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=false annotation, the description discloses the critical asynchronous behavior (immediate job id, polling required, completion condition) and the requirement that the URL be publicly reachable. It does not mention error handling or auth, but the disclosed async pattern is significant and adds value.

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: the first defines the core function, the second gives the essential async workflow, and the third identifies the batch API endpoint. 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?

Given the tool's complexity (15 params, async behavior, no output schema), the description covers the most critical missing context: the async flow and where to find the transcript. It doesn't explain error handling or deletion, but the schema covers parameters and the description provides a complete workflow for the primary use case.

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 detailed descriptions for all 15 parameters. The description adds a high-level overview (diarization, translation, summarization) but does not provide any additional parameter-level meaning beyond what the schema already offers. 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 clearly states the tool's function: submit a publicly reachable audio/video URL for speech-to-text transcription. It mentions optional features (diarization, translation, summarization) and the async nature. It distinguishes itself from sibling tools by being the only creation/submission tool; siblings are all retrieval/deletion.

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

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

Provides explicit workflow guidance: 'ASYNC: returns a job id immediately — poll speechmatics_get_job until status is "done", then call speechmatics_get_transcript.' This tells the agent how to use the tool and which siblings to call next. It lacks an explicit 'when not to use' or alternatives, but the async workflow and the fact that it's the only submission tool among siblings makes usage clear.

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