Transkripce – Czech audio and video transcription

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

Annotations only declare readOnlyHint=false, idempotentHint=false, destructiveHint=false. The description adds real value beyond that: the return value (payment_url), the fact that credits are granted asynchronously after payment, and the required transcription:write scope. It leaves idempotency behavior unaddressed despite idempotentHint=false, so repeated calls likely create multiple links — a noteworthy gap.

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?

Front-loaded with the core action in the first sentence, followed by supporting detail. There is mild redundancy between "human pays, not the agent" and "The agent never touches a card or payment method," though the emphasis is arguably intentional for safety.

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 an output schema present, the description need not detail return fields, and it still usefully names payment_url. For a checkout-creating mutation it covers auth scope and post-payment behavior, but omits link expiry, idempotency, and what happens if the human never pays.

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

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

Schema description coverage is 0% for the single parameter package_id, so the schema provides only the name and type. The description's phrase "for a credit package" implies the parameter's meaning but gives no format guidance (identifier vs name) or where to find valid values.

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 ("Prepare a Stripe payment link for a credit package") and immediately scopes who acts ("human pays, not the agent"). This clearly separates it from siblings like transcription_list_credit_packages and transcription_get_credit_balance, which read credit data rather than create a checkout.

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 human-in-the-loop framing gives a clear condition for use: when a human account owner needs to add credits. It does not explicitly say how to obtain a valid package_id (presumably via transcription_list_credit_packages), nor does it state any exclusions or limits on when a checkout should be created.

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 covered. The description adds that the estimate is derived solely from duration, which usefully signals it is an approximation and not a quote, but it says nothing about precision, rounding, or whether per-workflow settings affect the figure.

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

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

A single front-loaded sentence with no filler; every clause carries information. Slightly terse given the ambiguity around what the returned credits mean.

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

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

An output schema exists, so return-value explanation is not required, and for a one-parameter calculator the description covers purpose plus units. The remaining gap is what the estimate is based on (quality tier, model) and how authoritative it is.

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

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

Schema description coverage is 0%, so the description must carry the unit — and it does by stating '(seconds)' next to duration. It adds nothing further: no guidance on fractional values, minimum duration, or whether the value must match an actual audio file's length.

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 ('Estimate') and resource ('credit cost of transcribing audio') and names the driving input (duration in seconds). That makes it clearly distinct from credit-balance or package-listing siblings, though it never explicitly names those siblings.

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

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

There is no explicit when-to-use statement or named alternative, but the wording ('estimate cost ... of the given duration') strongly implies a pre-flight check before starting a transcription. The agent must infer that context rather than being told.

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 covered and the bar is lower. The description adds that the balance is split into total/reserved/available, which is genuinely useful context about the shape of the data, but it offers nothing on freshness, currency, or account scoping.

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

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

A single front-loaded sentence with the resource stated first and the returned breakdown in parentheses. Nothing is wasted and nothing needs trimming.

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

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

An output schema exists, so return values need no explanation, and annotations cover the read-only nature. For a zero-argument query tool this is nearly complete; only the alternative-routing context is absent.

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

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

The tool takes zero parameters, so the baseline is 4 and there is nothing the description needs to disambiguate. Schema coverage is 100% and there are no arguments to misinterpret.

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 ('Get your prepaid credit balance') and even enumerates the components returned (total, reserved, available). It is clearly distinct from siblings like transcription_estimate_cost or transcription_list_credit_packages, though it never explicitly names those siblings to route the agent.

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

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

No guidance on when to call this versus transcription_estimate_cost (cost projection) or transcription_list_credit_packages (purchase options), nor any prerequisite or timing guidance. Usage is implied by the tool name rather than stated.

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

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

The annotations already declare this a safe read (readOnlyHint true, destructiveHint false), so the description only needs to add context. It contributes the download semantics, the output file formats, and the completed-workflow precondition, but says nothing about failure behavior for incomplete workflows or report availability timing.

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

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

A single sentence with the action and the artifact front-loaded and a parenthetical covering the format options. No redundant or filler wording.

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

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

An output schema exists, so return values need not be described, and annotations cover safety. The remaining gaps are the undocumented required workflow_id semantics and the lack of guidance on the precondition failure case, which matter for a two-parameter tool with zero schema coverage.

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

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

Schema description coverage is 0%, so the description carries added burden. It does add real value by naming the allowed formats ('txt/md') that the schema leaves as an unconstrained string with a default, but it explains nothing about workflow_id beyond the implied 'completed workflow' constraint.

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 (download) plus a specific artifact (quality audit report) scoped to a completed workflow, which distinguishes it from transcription_get_transcript and transcription_get_workflow. It stops short of naming those siblings explicitly, so an agent must infer the boundary.

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 'of a completed workflow' implies a precondition and therefore a usage context, but there is no explicit when-to-use, no routing to a sibling for in-progress workflows, and no mention of what happens if the workflow has not finished.

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 covered. The description adds the meaningful constraint that only "final merged" transcripts of "completed" workflows are returned, implying this is not a live/partial read. It does not say what happens on an incomplete or failed workflow, which is the main behavioral unknown for a read tool with annotations present.

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

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

A single front-loaded sentence with no filler; the scope constraint and format options are packed in without redundancy. Nothing could be removed without losing 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?

The tool is simple, has an output schema (so return shape need not be described), and annotations cover safety, so the core is present. The remaining gap is failure behavior for unfinished workflows and any note on when md/json differ in content — small but relevant for correct 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 coverage is 0%, so the description must compensate. It does so for the format parameter by enumerating txt/json/md, which the schema does not (format has no enum). For workflow_id it adds only the implicit "must reference a completed workflow" context, leaving the identifier's provenance undocumented.

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 gives a specific verb and resource ("Download the final merged transcript") plus a scope qualifier ("of a completed workflow") and enumerates output formats. It is clearly distinguishable from siblings like transcription_get_quality_report or transcription_get_workflow, though it never names them 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?

The phrase "of a completed workflow" implicitly tells the agent this only applies after a workflow finishes, which is useful context. However, there is no explicit when-not guidance, no mention of what to do while a workflow is still running, and no pointers to the sibling that supplies the workflow state.

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 this as a safe, non-destructive read, so the description's main contribution is the field preview (status, error, billing, job IDs), which hints at the polling/inspection use case. It adds no context on auth, rate limits, or staleness of workflow state, so the gain over the annotations is modest.

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 short sentence with the resource and lookup key front-loaded and the return fields compactly bracketed. Nothing here is redundant or padded.

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 with an output schema and safety annotations, the description covers purpose and expected payload adequately; return-value explanation is correctly offloaded to the output schema. Only the provenance and format of the required ID 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 description coverage is 0% for the single parameter, so the description must carry the semantic load. 'By ID' confirms workflow_id selects a specific workflow, but says nothing about the expected ID format or how to obtain a valid ID, adding only marginal meaning beyond the parameter name and title.

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 names a specific verb and resource ('Get one transcription workflow') and narrows the scope to an ID lookup, with a parenthetical enumerating the returned fields (status, error, billing, job IDs). This implicitly separates it from transcription_list_workflows, though no sibling is named 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?

Usage is implied: use this when you already hold a workflow ID and need its current state. There is no explicit guidance on when to prefer it over transcription_list_workflows, nor any statement about prerequisites or where the ID comes from, leaving the agent to infer the routing.

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 safety is covered structurally. The description adds real behavioral context by disclosing that only files the caller has uploaded are returned and that IDs are consumable by another tool. It does not mention whether results are paginated, ordered, or truncated, which is the main remaining behavioral unknown.

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

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

A single sentence with the action front-loaded and the useful downstream hint compactly placed in parentheses. No filler, no restatement of the tool name, and 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 parameterless read-only tool with no output schema, the description covers what it returns at a conceptual level (audio files and their IDs) and how the result is consumed. The only gap is the shape of each returned entry and any pagination behavior, which the agent would have to discover at runtime. Given the tool's low complexity and the annotation coverage, it is nearly complete.

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

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

The tool takes zero parameters, so by the stated baseline this scores 4; there is nothing for the description to disambiguate. The parenthetical does convey downstream meaning about the returned identifiers, which is a small bonus even though it concerns output rather than 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?

The description states a specific verb and resource ('List audio files') and narrows scope with 'you have uploaded', so the agent knows this is user-scoped rather than global. It also names the downstream consumer (transcription_start_workflow), which separates it from the workflow, credit, and transcript retrieval siblings. It stops short of explicitly distinguishing itself from the other listing tools in the family.

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 context is implied by the parenthetical noting that returned IDs are usable in transcription_start_workflow, which effectively documents the follow-up step. However, there is no explicit 'use this when...' framing and no exclusions telling the agent when another listing tool is the better choice. The guidance is adequate but must be inferred.

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 covered. The description adds that the listing is public and denominated in CZK, which is real context, but says nothing about ordering, package availability, or authorization beyond the word "public".

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 short sentence, front-loaded with the verb and resource, with the parenthetical scoping the content. No wasted wording.

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 zero-parameter, read-only listing tool with an output schema, the description covers what the tool returns conceptually (purchasable packages with CZK prices). Nothing critical to correct invocation is missing, though linking it to the checkout sibling would complete the picture.

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 are zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The mention of a public CZK price list usefully frames what the (output-schema-described) rows represent.

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

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

States a specific verb and resource ("List purchasable credit packages") and clarifies the resource with the parenthetical "public CZK price list," so an agent knows this is a catalogue of buyable packages rather than balances or costs. It is distinguishable from siblings like get_credit_balance and estimate_cost, though it never names those alternatives.

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?

"Purchasable" implies this is consulted before a top-up/checkout flow, but the description never states when to use it versus transcription_create_topup_checkout or transcription_get_credit_balance. Usage is inferable rather than explicit.

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 covered. The description adds a real behavioral detail — results are ordered newest first — plus a hint at returned fields (status, IDs, billing). However, it says nothing about pagination or how many results are returned by default, which matters for a list tool.

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

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

One front-loaded sentence with zero filler; purpose, ordering, and returned fields all appear immediately. Nothing is wasted or buried.

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?

Complexity is low, there is an output schema so return values need no explanation, and the single optional parameter is standard. The only real gap is the undocumented limit behavior, which is minor for a one-parameter list 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?

There is one optional parameter (limit) with 0% schema description coverage, and the description does not explain what it controls or its default of 20. The 'newest first' note does imply ordering semantics tied to the list, but it does not compensate for the undocumented limit, leaving the parameter meaning thin.

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 pairs a specific verb (list) with a specific resource (your transcription workflows), and adds ordering and returned-content hints. It is clearly distinguishable from the singular sibling transcription_get_workflow, though it never names that sibling 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?

There is no when-to-use guidance, no exclusion stating that transcription_get_workflow should be used for a single workflow, and no prerequisites mentioned. Usage must be inferred from the verb alone.

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

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

Adds substantial context beyond the annotations: the required transcription:write scope, the credit reservation model (1 credit per started minute), and two specific failure codes (INSUFFICIENT_CREDITS, AGENT_KEY_BUDGET_EXCEEDED). It does not warn about the interaction between idempotentHint=false and credit reservation (a retry may double-charge), which is the one meaningful behavioral gap.

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?

Front-loaded with the action, followed by requirements and failure modes in a logical order; every sentence carries information. Slight verbosity in the multi-line error-code enumeration, but nothing is wasted.

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 output schema removes the need to describe return values, and the cost/auth/error disclosure is strong for a mutation tool. However, three optional parameters are undocumented in both schema and description, which is a real gap for an agent trying to configure diarization or provider selection.

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

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

Schema description coverage is 0%, so the description carries the full burden, yet it explains none of the four parameters. providers, diarization_enabled, and max_duration_seconds are opaque — an agent cannot tell what provider names are valid or what max_duration_seconds constrains (upload length vs. transcription cutoff) from the description or schema.

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

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

States a specific verb ('Start') plus the resource ('automatic transcription workflow') and even names the internal pipeline stages (transcription -> merge -> quality). This clearly separates it from siblings like transcription_get_workflow or transcription_list_workflows, which are read operations on existing workflows.

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 states the prerequisite ('Upload audio first via REST POST /api/v1/transcription/audio-files'), which is the key precondition for calling this tool. It does not name alternatives (e.g., estimate_cost or get_credit_balance before starting), leaving that inference to the agent, but the usage context is clear.

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