convert.express

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

The description adds meaningful behavior beyond the annotations: it discloses that the page is public, anyone with the link can view it, and access lasts until the job expires. It also implies the job must be completed. With annotations already covering open-world and idempotent behavior, this additional exposure and lifetime context is valuable.

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 communicate the artifact, audience, public visibility, and expiration with no wasted text. The key outcome is front-loaded and the security implication follows immediately.

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

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

For a simple two-parameter tool with rich annotations and full schema coverage, the description covers the main artifact and visibility behavior. It does not explicitly state that a link/URL is returned, but the concept of a public web page is sufficient for invocation 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?

Schema description coverage is 100%, and both parameters are already well documented in the input schema. The description adds no parameter-specific details, so the baseline score of 3 applies when the schema carries the parameter semantics.

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

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

The description clearly identifies the resource created: a public web page containing a completed job's results, intended for sharing. It does not explicitly say 'creates a share link' or distinguish this tool from siblings like get_job, but the outcome is specific enough to infer the action.

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 phrase 'for your user to open or send to others' implies the sharing use case, but the description does not explicitly say when to use this tool versus alternatives such as get_job or list_jobs. Usage is therefore only implied rather than stated with clear conditions or exclusions.

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 cover the safety profile (readOnly=false, destructive=false, idempotent=false), so the description is free to add what they cannot: the two-URL return contract, the HTTP PUT requirement, and the fact that a browser upload auto-starts transcription. It does not address whether calling twice creates duplicate uploads (relevant given idempotentHint=false) or any auth requirements.

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, zero filler: the eligibility condition comes first, then the return contract with the action required for each URL. The parenthetical example ('a file attached in another chat app') is doing real disambiguation work.

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 10 parameters, no output schema, and full schema coverage, the description fills exactly the gap that matters: what the call returns and what to do with each return value. Nothing an agent needs in order to invoke this correctly 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 description coverage is 100%, so filename, content_type, size_bytes, model, and the boolean extras are already well documented in the schema. The description adds no parameter-level meaning — upload_url and upload_page_url are return values, not inputs — so the baseline 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 scopes the tool to files that are neither public links nor ChatGPT attachments, which is a meaningful resource distinction. It never names the sibling tools (transcribe_url, transcribe_file) that handle the excluded cases, so the agent must infer the routing from the negative condition rather than being told outright.

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 when-not condition is explicit (not a public link, not a file attached in a ChatGPT chat) and the follow-up workflow is spelled out: PUT the file to upload_url then call start_transcription, naming that sibling directly. The alternative path (upload_page_url for a browser upload) is also given. The only gap is that the tools to use for the excluded cases are never named.

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 destructiveHint=true and idempotentHint=true, so the safety profile is covered structurally. The description adds real value by enumerating exactly what is destroyed (uploaded file, transcript, all results) and framing it against the 24-hour auto-deletion window, which an agent could not infer from annotations alone. It does not describe failure behavior for already-deleted jobs, a minor gap given idempotentHint.

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, zero filler, with the destructive scope front-loaded and the 'Cannot be undone' warning closing it. Every clause carries 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 two-parameter destructive tool with full schema coverage, complete annotations, and no output schema, the description supplies what is needed: what is removed and the irreversibility. Only the post-success response shape and auth failure modes are unstated, both low-impact here.

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 both job_id (with format/pattern and provenance from transcribe_url or create_upload) and robot_key are already documented in the schema. The description adds no parameter-level meaning, which is acceptable at full coverage but leaves it at baseline.

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

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

States a specific verb (delete) plus the exact resources affected (uploaded file, transcript, all other results), and contrasts it with the default lifecycle (automatic deletion within 24 hours). No other sibling tool deletes jobs, so it is trivially distinguishable from get_job, list_jobs, and the transcription tools.

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

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

The phrase 'right away, instead of waiting for the automatic deletion within 24 hours' gives a clear condition for choosing this tool over doing nothing. It stops short of explicit exclusions or prerequisites (e.g., only for jobs you own), but the usage context is 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 establish read-only, idempotent, non-destructive behavior, so the description adds useful context beyond them: it discloses that the estimate is in EUR, includes price_usdc when USDC is enabled, and returns user account details for linked robots. It does not cover auth requirements or rate limits, but it materially enriches the behavioral picture.

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 dense sentences with no filler. The primary pricing purpose is front-loaded, followed by the conditional account-information behavior.

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, the description carries return-value burden and does a good job listing the key outputs: EUR price, optional USDC price, and account-specific details for linked robots. It stops short of describing exact response fields or edge cases, but it is sufficient for an agent to invoke the tool and interpret the main results.

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, but the description adds meaning by indicating that robot_key determines whether user-specific account information appears. It also clarifies that duration_minutes represents recording length, reinforcing what the schema already says.

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

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

The description states a specific action and resource: pricing a transcription for a recording of a given length. It also names the currency output and a conditional USDC price, making the tool's purpose clear, though it does not explicitly distinguish itself from siblings such as start_transcription or get_service_info.

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?

Usage is implied by the pricing framing, but there is no explicit guidance on when to call this versus alternatives or on prerequisites. The conditional note about linked robots adds context but does not establish when/when-not to use the 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?

Annotations already cover read-only/idempotent/non-destructive, and the description adds a full status state machine beyond that: what each state returns (transcript formats, download links, zip_url, summary, action_items, translations; 100-word preview plus payment_url; error message) and the 24-hour deletion window. This is exactly the behavioral context annotations cannot express.

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?

Purpose and job_id provenance are front-loaded, then each status is quoted and paired with its payload in a compact clause. Roughly 110 words with no filler — every sentence conveys a state, a polling rule, or a return value.

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?

No output schema exists, so the description carries the full burden of describing returns — and it does so per status, including the ZIP aggregate, preview/payment path, and failure/deletion cases. An agent has everything needed to call it, poll it, and interpret each response.

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, but the description still adds provenance for job_id (including transcribe_file, which the schema omits) and ties the format parameter to its output consequence ("the transcript in the chosen format"). robot_key is left entirely to the schema, which keeps it from a 5.

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

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

States a specific verb+resource ("Status and results of one job") and immediately scopes it to a known job_id. It also names the sibling tools that produce a job_id (transcribe_url, transcribe_file, create_upload) and the sibling that recovers a lost one (list_jobs), so it is distinguishable without opening any schema.

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?

Gives explicit when-to-call guidance per state: poll every 10-20 seconds while waiting_for_upload/queued/processing, call again after the user pays on payment_required, and use list_jobs when the job_id is lost. The alternative tool and the condition selecting it are both named.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false; the description reinforces this with 'takes no parameters and changes nothing' and adds genuinely new context by itemizing the return payload (pricing, limits, privacy). It omits any auth or rate-limit detail, so not a 5.

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 call-first trigger before the payload inventory. The field enumeration is dense but justified given there is no output schema to carry that 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?

With no output schema in the definition, the description must characterize the return value itself, and it does so by naming every top-level section. Nothing an agent needs to call a zero-parameter discovery tool 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?

Zero parameters, so the baseline is 4; the description confirms this explicitly with 'Takes no parameters,' which removes any ambiguity an agent might have about passing optional input.

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

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

States a specific verb and resource ('Returns one JSON object' describing the convert.express service) and enumerates the payload sections, so an agent knows exactly what it gets back. It also positions itself against the siblings by framing itself as the discovery tool to consult before estimate_cost/start_transcription.

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?

Gives three concrete triggering conditions: new to the service, before quoting a price, or when unsure about file/link/language support. That implicitly routes pricing to estimate_cost and capability questions here, but no sibling is named explicitly, which keeps it short of a full 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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: jobs disappear within 24 hours of creation and results are newest-first. It does not mention result size limits or pagination, keeping it below a 5.

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?

One compact sentence with the scoping constraint front-loaded and the retention caveat in a parenthetical. Every clause (existence, retention window, ordering, status field) carries information an agent needs.

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

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

The tool is simple (one required param, no output schema, read-only), and the description covers scope, ordering, and the fields returned, which is enough to call it correctly. Only the absence of any mention of result count or pagination leaves a small gap.

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

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

There is a single parameter with 100% schema description coverage, including the note that robot_key is required to read or start jobs, so the schema carries the meaning. The description adds nothing parameter-specific beyond the word "Your", which is the expected baseline of 3.

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

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

States a specific resource and scope ("Your jobs that still exist"), plus ordering (newest first) and returned field (status). It clearly reads as a plural list operation, distinguishing it implicitly from the singular get_job sibling, but never names or contrasts with that sibling.

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?

Usage is only implied — an agent must infer that this is the polling/discovery call and that get_job is for a specific job. The 24-hour retention note hints at why a job may be missing, but no explicit when-to-use or when-not-to-use guidance is given.

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 openWorldHint, idempotentHint, and destructiveHint. The description adds valuable protocol behavior beyond that: an initial call yields a payment challenge with currency-specific pricing, and an MPP client pays then calls again. It does not discuss idempotency or charge-reversal implications, but with annotations covering the safety profile this is a strong addition.

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?

Four sentences, front-loaded with the trigger condition, followed by the payment challenge flow and the no-wallet fallback. No sentence is redundant, and the alternative path is placed last as a natural exception.

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?

Covers the critical invocation behavior: precondition, challenge response, currency behavior, retry flow, and fallback path. It does not explain what a successful paid response contains, but without an output schema that is a minor gap given how well the payment flow is described.

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 both parameters, so the schema already carries parameter meaning. The description does not add syntax or format details beyond the schema, but it does not need to; baseline 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?

States a specific verb (pay), resource (full transcript of a job), and precondition (get_job status is 'payment_required'). It also explicitly references sibling get_job, making the distinction from status-checking tools obvious.

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 when to use it (job in payment_required status) and gives a clear alternative when no MPP wallet exists: show payment_url from get_job instead. The two-step call-without-payment-then-retry flow is spelled out.

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

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

Annotations already declare non-read-only, idempotent, non-destructive, but the description adds the genuinely necessary behavior: the call returns immediately and results must be polled via get_job. It omits whether re-requesting regenerates or re-bills the summary, which matters given the pay_job/estimate_cost siblings.

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, zero waste, with the trigger action front-loaded and the async read path immediately after 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, the description correctly handles the return-value question by pointing to get_job and naming the summary/action_items fields. Only the cost/regeneration semantics and permission requirements are left unaddressed.

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 each parameter, including the type enum and the robot_key requirement, is already documented in the schema. The description adds no syntax, format, or constraint detail beyond it, so the baseline 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?

States a specific verb and resource: request an AI summary or action items for a completed job. It also distinguishes itself from get_job by explaining that get_job is the read path for the output, so the agent understands this tool only triggers the work.

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?

"of a completed job" gives an explicit precondition, and "the result appears in get_job" tells the agent the follow-up call to make. No when-not-to-use guidance is given, but no obvious competing sibling exists for this action.

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

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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent call, so the safety bar is partly covered. The description adds genuinely new behavior: a human reads every message, there is no automatic reply, and the consent requirement for reply_email. Rate limits, expected latency, and what happens to an existing robot_key are not covered.

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 tight sentences with zero filler; the purpose and the human-review expectation are front-loaded, and the conditional reply_email rule trails appropriately.

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 full schema coverage, the description needs only to convey expectations and consent policy, which it does. It leaves unexplained what the agent receives back (a robot_key on first call) even though the schema hints at 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?

Schema description coverage is 100%, so all four parameters (including the type enum and message length cap) are already documented in the schema. The description's only added parameter context — reply_email requires the user's consent — duplicates the schema's own wording. Baseline 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?

States a specific verb and resource ('Tell the convert.express team about a bug, a missing feature, or a question') and enumerates the exact categories covered. It is clearly distinguishable from every sibling tool (transcription, upload, job management) without opening any schema.

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 makes the triggering conditions clear via the enumeration of message types and adds a conditional rule ('Include reply_email only if your user wants an answer'). It does not state when not to use the tool or point to any alternative channel, so it falls short of a full 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 cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), so the bar is lower. The description usefully adds that the call validates file presence and queues work rather than returning a finished transcript, but it says nothing about failure behavior if the file is missing, cost implications, or how to poll for results.

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, no filler, with the prerequisite call ordering front-loaded. Every clause carries information an agent needs.

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 fully documented parameters, no output schema, and annotations covering safety and idempotency, the description supplies the essential missing piece (the prior upload step plus queueing semantics). It could go further by noting that completion must be polled via get_job and whether payment is required.

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%: job_id's origin (transcribe_url or create_upload) and robot_key's purpose are both documented in the schema. The description adds no parameter meaning, so the baseline 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?

States the action concretely: it verifies the uploaded file arrived and queues it for processing, which pairs with the name start_transcription. It is implicitly distinguished from create_upload/transcribe_url by the 'after the PUT' sequencing, but never names those siblings explicitly.

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

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

"Call after the PUT to upload_url has finished" gives an explicit timing prerequisite, which is the key piece of when-to-use guidance for this tool. It stops short of naming alternatives or stating when not to call it (e.g., before upload completes, or without payment).

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 only cover safety/mutability flags; the description adds real behavioral context the agent could not infer — that the chat client fills in the temporary download URL, that convert.express downloads from it, and that the tool is asynchronous (returns job_id, then poll get_job). It omits the non-idempotency implication (repeated calls spawn new jobs, consistent with idempotentHint=false) and any cost/auth expectations, so it earns a 4 rather than 5.

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?

Four short sentences, zero filler. The primary action and its environment constraint come first, the alternative routing second, and the follow-up step last — perfectly front-loaded for an agent scanning for actionability.

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 an 8-parameter, nested-object, async tool with no output schema, the description supplies the missing lifecycle piece (job_id then get_job) that the schema cannot express. It leaves unstated whether jobs incur cost or must be paid via pay_job, and does not note that repeated calls create separate jobs, which are small but real gaps given the sibling tools available.

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%, including the nested file object, model enum guidance pointing at get_service_info, and the robot_key explanation, so the schema carries the parameter burden. The description adds nothing parameter-specific beyond the download_url mechanics already documented in the schema, making baseline 3 correct.

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

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

States a specific verb and resource ("Start transcribing an audio or video file") plus the scope constraint that the file must be attached in a ChatGPT chat. The sibling set includes transcribe_url, start_transcription, and create_upload, and the description makes clear this one is the attached-file path without needing to open any schema.

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?

Articulates the selection condition (file attached in a ChatGPT chat) and explicitly routes the agent elsewhere for the main alternative case: "Other chat apps cannot fill in that link: use create_upload for files attached there." It also tells the agent what to do next after the call (poll get_job).

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

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

Annotations already declare this is a non-read-only, non-idempotent, open-world call, and the description usefully adds the async job pattern and the job_id/robot_key return values. It says nothing about cost or credit requirements, which matters given the estimate_cost and pay_job siblings, nor about limits or duplicate-job behavior implied by idempotentHint=false.

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, zero waste: what it does and what to do next. The workflow pointer is front-loaded in the second clause.

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, the description correctly discloses that the call returns job_id and robot_key and how to continue with get_job, which is the minimum an agent needs. The missing piece is the monetization/allocation context hinted at by the pay_job and estimate_cost 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 coverage is 100%, so every parameter is already documented in the schema, including the model enum and the robot_key carry-over rule. The description only reinforces the robot_key lifecycle by noting it is returned; baseline 3 applies when 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?

States a specific verb and resource ("Start transcribing a media file") and qualifies the source as "a public link", which separates it from transcribe_file. It does not distinguish itself from the sibling start_transcription, so an agent comparing those two still has to infer the difference.

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

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

"Returns job_id and robot_key; then poll get_job" gives explicit follow-up guidance and names the sibling to use next. It stops short of stating exclusions (e.g., when to prefer transcribe_file or start_transcription), but the link-vs-file condition is clearly implied.

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 idempotentHint=true, destructiveHint=false, and readOnlyHint=false, so the safety profile is covered. The description adds genuinely non-structured behavior: the call is asynchronous and returns immediately despite being a write operation, and the output lands in get_job under a 'translations' key, plus the note that subtitle timecodes are preserved. Rate limits, credit cost, and failure modes are not mentioned.

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 tight sentences. The capability comes first, then the result-retrieval hint, with the useful 'timecodes kept' parenthetical folded in rather than padding. Nothing is wasted or restated from the schema.

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, the description correctly fills the gap by explaining that the call returns immediately and where the translation surfaces (get_job → translations). The 'completed job' precondition and source prerequisites are covered. Minor omissions: no mention of cost/credit implications or behavior when the target language or source artifact is unavailable.

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 every parameter including the source enum and its default are already documented in structured data, making 3 the correct baseline. The description's mention of which sources exist and that timecodes are kept marginally reinforces the 'srt/vtt/timed' enum semantics, but adds no new syntax or constraints.

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

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

States a specific verb (translate) and enumerates the exact resources it operates on (transcript, subtitles, summary, action items) constrained to 'a completed job'. This is unambiguous and clearly distinct from sibling tools like request_summary, get_job, or start_transcription.

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?

'Of a completed job' establishes the precondition for invocation, and the closing sentence routes the agent to get_job to retrieve the result, which is a clear next-step pointer. It stops short of stating exclusions (e.g., that summary/action_items must already exist is left to the schema, and no alternative tool is named for pre-completion cases).

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