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

With no annotations, the description must carry the full behavioral burden, and it does disclose one genuinely non-obvious trait: the call consumes no credits, which matters for agent planning. However, it never states permission requirements, whether the board name must be unique, what the response contains (e.g. a board id), or what happens on failure, so mutation semantics remain largely opaque.

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

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

Two short sentences, action stated first, cost disclosure second. Nothing is padded and nothing repeats the tool name.

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 one-parameter creation tool with no output schema this is the minimum viable amount: it explains the action and the credit cost. It is still missing what the caller gets back and how the board relates to other creation paths, which matter for a mutation tool with zero annotation 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% and the single required parameter "name" is never mentioned in the description. That name maps to the board's name is inferable from context, but constraints (non-empty, minLength 1) and any naming rules are left entirely to the schema, which says nothing.

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?

"Create an empty board" is a specific verb plus resource, and the word "empty" distinguishes it from creation paths that pull in external content (e.g. recreate_from_link). It stops short of naming a sibling explicitly, so it lands at 4 rather than 5.

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 gives no when-to-use guidance, no prerequisites, and no mention of the alternative creation route (recreate_from_link) that an agent might otherwise consider. The reader must infer the choice entirely.

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

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

With no annotations supplied, the description carries the full burden and does contribute one valuable operational fact: the call spends no credits, which tells an agent it is a cheap read. Beyond that it discloses nothing about error behavior for a missing board, whether the read is permission-gated, or whether pieces are paginated.

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, the retrieval purpose front-loaded and the cost note second. Nothing is padded and no sentence is redundant.

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

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

There is no output schema, so the description has to convey the return shape, and "and its pieces" only gestures at it without describing the pieces' fields or count. For a one-parameter read tool this is close to adequate, but the pricing note is the only real context added.

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 single required board_id is documented only by its name in the schema. The description's "one board" signals that board_id selects a single record but adds no format, source, or lookup guidance. Because the schema has just one self-evident string parameter, the practical cost of the gap is small.

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?

"Get one board and its pieces" names a specific verb (get), a specific resource (board), and the payload returned (its pieces), which cleanly separates it from the sibling list_boards. It stops short of 5 only because it never states what a "piece" is or how the single-board scope relates to other retrieval 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?

The word "one" implies this is the single-record fetch versus the plural sibling list_boards, so an agent can infer usage. There is no explicit when-to-use, no mention of what happens on an unknown board_id, and no named alternative such as get_run or get_run_assets.

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

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

With no annotations, the description carries the full load, and it does disclose one genuinely useful behavioral trait: the call is free of credit cost, which matters for repeated polling. It says nothing about read-only semantics, authentication, or what happens when run_id is unknown or the run is still in progress.

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 with no filler, and the return contents are front-loaded. 'Charge' on its own is slightly ambiguous, reading as either the cost incurred by the run or a billing field, which costs it a point.

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?

It is a simple tool with one required parameter and no output schema, so the description only needs to cover what it returns and how to call it. The return contents are covered and the cost behavior is disclosed, but the sole parameter is entirely unexplained and there is no guidance on polling or error cases.

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 single parameter run_id is documented nowhere, and the description does not compensate by explaining its format or where it comes from. For a one-parameter tool it is the only semantic gap, but it is a complete one.

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 the resource ('Run') and the three things it returns (status, charge, outputs), which is more specific than a bare name restatement. It does not differentiate from the closest sibling, get_run_assets, which also exposes run-level data, so the boundary between the two is left for the agent to infer.

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?

'Spends no credits' implies it is cheap and safe to call, which hints at polling use, but the description never states when to use this tool versus get_run_assets or the other run-related siblings. No prerequisites, no exclusions, no alternative 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?

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses two traits — links expire ('temporary') and the call is free ('spends no credits') — but omits link lifetime, whether links are publicly accessible without auth, whether all outputs are covered, and whether repeated calls regenerate links.

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, front-loaded with what the tool returns and followed by the cost caveat; nothing is wasted. The telegraphic fragments are efficient rather than 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 one-parameter read tool with no output schema, the core is covered: it returns links and costs nothing. Missing expiry behavior, response shape (list vs map of links), and whether the links point to all outputs or a subset keep it at minimum-viable rather than 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?

Schema coverage is 0% for the single run_id parameter, so the description must compensate. 'A run's outputs' does implicitly convey that run_id selects which run's artifacts are returned, but it adds no format, source, or validity guidance for the identifier.

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?

Names a concrete resource — temporary download links for a run's outputs — which is clearly distinct from siblings like get_run (run metadata) and quote_video/plan_edit (analysis and editing). It is a noun phrase rather than a verb phrase, so the agent must infer the action is 'fetch/return links', but the scope of the resource 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?

'Spends no credits' is a useful selection cue implying this should be preferred over billed retrieval paths, and 'temporary' hints at when the result is appropriate. However, it never states when to call this instead of get_run, nor whether it should be called before or after other run operations.

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

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

No annotations are supplied, so the description bears full behavioral burden. It usefully discloses the cost trait ('Spends no credits'), which matters in a credit-metered API, but says nothing about the result shape, ordering, or pagination for workspaces with many boards.

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, front-loaded with the action and scope, with the cost note last. Nothing is wasted and nothing is 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?

For a zero-parameter list tool with no output schema, the description covers what is listed, where, and the cost. A note on whether results are paginated or complete would close the remaining 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?

The tool takes zero parameters and the schema is empty, so there is nothing for the description to disambiguate. Baseline 4 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?

Specific verb plus resource ('List boards') scoped to 'your Reelo workspace', which is clear enough to distinguish it from mutating siblings like create_board and single-item siblings like get_board. It stops short of explicitly naming a sibling to route against.

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 or when-not-to-use guidance and no reference to alternatives such as get_board for a single board. The only implicit guidance is the credit-cost note, which implies it is a cheap call but does not say when to prefer it.

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

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

With no annotations, the description carries the full burden, and it does disclose two important traits: no credits are spent and a render_quote (in whole credits) is returned. However, it never says whether the planned Edit node is persisted on the board, whether re-planning overwrites prior plans, or what permissions/board state are required — significant gaps for what appears to be a mutating planning call.

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 short sentences, each doing distinct work: scope + capability list, cost behavior, then the required workflow. Front-loaded with the action and no filler or restated title.

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

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

There is no output schema, and the description compensates partially by naming the render_quote return and its unit. For a six-parameter tool with a nested freeform ops array, though, the definition leaves the caller without enough to construct a valid ops payload or understand board_id/voice_id, so it is only adequate relative to the tool's complexity.

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 50%, and the description usefully explains that output_seconds and ratios are what drive the render_quote, which goes beyond the schema. But the most complex parameter, `ops`, is a freeform array with only an `op` string required and no shape documented anywhere; the parenthetical list hints at op kinds but gives no structure, and board_id/voice_id remain completely unexplained.

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 ("Plan an Edit node") and enumerates what that node can express (join, trim, text, captions, duck music, effects), which makes the tool's scope concrete. It also states the payoff — a render_quote — but does not explicitly contrast itself with siblings like quote_video or run_quote, leaving that distinction to inference.

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 gives clear situational guidance: this is the no-credit planning step, and the returned price must be shown to the user before they approve the render in the app. That establishes a workflow position. What's missing is an explicit when-not or a named alternative for callers who want to skip planning and go straight to quoting or rendering.

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

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

With no annotations, the description usefully discloses that the call 'spends no credits', establishing it as a safe read-like operation, and names the return fields (quote_id, total_credits, clips, balance). It omits whether quotes expire, whether they are idempotent, and any auth or error behavior for a 10-parameter 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?

Four short sentences, front-loaded with purpose, then cost behavior, then return shape, then the workflow constraint. Nothing repeats and every sentence 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 10-parameter nested-schema tool with no output schema, the description covers purpose, cost, and return fields, which is meaningful. However it is silent on which mutually exclusive parameter paths (block vs duration vs duration_target) to use, leaving the most error-prone decision undocumented.

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 only 60% and the description adds no parameter meaning at all — no explanation of tier, ratio, resolution, or the interplay between block, duration, and duration_target. The description leaves the agent to infer mode selection entirely from the schema, so it fails to compensate for the coverage gap.

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 ('Quote a video in whole credits') and implicitly contrasts with run_quote by noting it spends nothing. The agent can tell this is the pre-flight cost estimate rather than the execution call, though the phrase 'in whole credits' is slightly opaque without reading further.

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 workflow routing: 'Always show the price to the user before run_quote' tells the agent this is the mandatory step preceding run_quote. It does not address when to choose block-based quoting versus duration/duration_target quoting, so parameter-selection guidance is absent.

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 zero annotations the description carries the full burden, and it does disclose two meaningful traits: no download occurs and no credits are spent. It omits other important behavior, such as whether any state is created on the board, whether the call is idempotent, and what the returned 'scene structure' contains.

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 short sentences, front-loaded with the core action, and every clause carries information. It is efficient, though the terseness contributes to the missing parameter and return-value detail.

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 four-parameter tool with no annotations, no output schema, and no schema descriptions, the description is too thin. It does not explain board_id or brief, does not describe the shape of the returned scene structure, and gives no indication of side effects beyond 'nothing is downloaded'.

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, and it only partially does: 'link' maps to url and '15 or 30 s' maps to the seconds enum (though the 15 s default is unstated). The required board_id and the optional brief are never mentioned anywhere, leaving half the parameters opaque.

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 concrete verb and resource ('Get a scene structure') and names the input ('from a link') plus the output's purpose ('to recreate a video'). It is clearly distinct from siblings like quote_video or plan_edit, though it never explicitly references them.

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: the 'nothing is downloaded / spends no credits' framing suggests a free preview step, and the 15/30 s limit scopes it. There is no explicit statement of when to use this versus quote_video or plan_edit, and no prerequisites or follow-up guidance.

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

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

With no annotations supplied, the description carries the full burden and does the most important part well: it discloses that credits are SPENT, held at start, and refunded on failure, plus the confirmation requirement. It omits whether the run is synchronous or async (and thus whether get_run polling is needed), how idempotency_key and webhook_url alter behavior, and what the call returns.

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 short sentences with the cost warning capitalized and front-loaded, then the preconditions. Every sentence earns its place and nothing is 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?

The critical financial/confirmation behavior is covered, which is the highest-value information for a credit-spending mutation. But with no annotations, no output schema, and 4 of 5 parameters undocumented, an agent still lacks enough to invoke and follow up on this tool reliably (e.g., polling vs webhook).

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% across 5 parameters, and the description only adds meaning for max_credits (must be >= the quote). board_id, quote_id, webhook_url, and idempotency_key are entirely undocumented, including the important retry-safety semantics of idempotency_key.

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 ('Run a quote') that distinguishes it from the sibling quote_video, which presumably creates the quote. However, it never explains what a 'quote' or a 'run' actually is, so an agent unfamiliar with the domain must infer the quote_video -> run_quote relationship.

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 a precondition ('Requires explicit user confirmation', 'max_credits >= the quote') which is genuine usage guidance, but gives no when-to-use vs alternatives routing — it never mentions quote_video, get_run, or get_run_assets, so the agent must infer the lifecycle position on its own.

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