Renderball

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

Beyond the minimal annotations (readOnlyHint=false, destructiveHint=false), the description discloses important behavior: sending an outline makes the reply carry the WRITING BRIEF, and without an account the tool returns a guest_token for later calls and a deck_url for the user. This meaningfully helps an agent anticipate outputs and side conditions, though it could say more about what happens when an account is 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?

Three sentences with no filler. The core action and key constraints come first, followed by workflow and return-value context. Every sentence contributes essential information an agent needs to invoke the tool correctly.

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

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

Given the complex nested schema and no output schema, the description covers the critical flow-level outputs: the WRITING BRIEF, guest_token, and deck_url. It also connects the tool to the larger two-step deck process. Minor gaps remain, such as explicit account-behavior details and any prerequisites beyond the schema, but the description is largely sufficient 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 description coverage is 100%, so the schema already documents every parameter in detail. The tool description adds emphasis on the brand contract ('never guess a colour') and the outline-to-writing-brief relationship, but it does not substantially expand parameter meaning beyond what the schema provides. Baseline 3 is appropriate.

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

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

The description uses a specific verb and resource ('Start a new presentation') and clearly differentiates this from siblings by framing the two-call workflow: 'this, then submit_deck'. It also makes clear the scope of inputs ('a brief, the brand as YOU know it... and your outline'), so an agent can identify what create_deck does versus write_outline or submit_deck.

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 concrete workflow guidance: with an outline, the response carries the WRITING BRIEF, making the whole flow just 'this, then submit_deck'. It also explains the guest case by noting a guest_token and deck_url are returned. It stops short of explicitly saying when not to use this tool versus write_outline or other siblings, but the intended creation flow is clear.

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

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

The readOnlyHint annotation already covers the safe, non-mutating behavior. The description adds useful context about what the agent can expect in the outcome (editor link for ready, reason for failure), but it does not discuss polling frequency, response format, or any edge cases.

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, compact sentence that immediately conveys the tool's purpose and key outcomes. No filler or redundancy.

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

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

Given the low complexity and no output schema, the description adequately covers the return behavior by naming the three states and what each provides. It could be slightly stronger on usage timing, but the core calling context is clear.

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 50%: guest_token is documented but deck_id is not. The description adds little beyond the schema, though 'a submitted deck' loosely connects to deck_idapiens. It does not clarify how guest_token should be used beyond the schema note.

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 (a submitted deck import) and the operation (checking its status), listing the possible outcomes: importing, ready, or failed. It is distinct enough from siblings like list_decks or see_deck, though it does not explicitly name 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?

The description implies the tool should be called after submitting a deck to poll its import progress, but it does not explicitly state when to use it versus alternatives or indicate that it is the only status-checking tool. No exclusions are provided.

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

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

The readOnlyHint annotation covers the safety profile, and the description adds a useful precondition: the outline must already be saved. It does not describe what happens if that precondition is unmet or what the response contains, but this is a simple read operation.

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 that leads with the resource and includes the key precondition; no filler or redundancy.

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

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

For a low-complexity, read-only tool with the parameter schema present, the description plus annotations cover the main usage context. The only notable omission is the lack of any hint about return content, but the title already conveys the core purpose.

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 schema documents guest_token's purpose and constraints, while deck_id is only type/length constrained. The description adds no parameter-level detail to compensate for the 50% schema coverage, so it adds little beyond the schema.

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

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

The title and description identify the resource as 'the writing brief' for a saved deck outline, which distinguishes it from siblings like see_deck and write_outline. It lacks an explicit verb in the description itself, relying on the title for 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 'whose outline is already saved' implies this is meant to be called after write_outline, but it never explicitly says when to use it over see_deck or other deck tools. It also does not state exclusions or alternative tools.

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

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

The readOnlyHint annotation already signals a safe read operation, and the description adds meaningful behavior beyond that: results are newest-first and include editor links, and authentication is required. It does not mention pagination or rate limits, but for a zero-parameter read tool this is a minor 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?

The description is compact and front-loaded: it opens with the core output, then states the one key prerequisite. There is no filler or repetition of the annotation; each fragment earns its place.

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

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

Given no output schema, the description does enough by stating what is returned (documents, editor links) and the ordering rule (newest first). It also covers the authentication prerequisite. It could be more explicit about the shape of each deck entry, but for a simple list tool this is sufficiently 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?

There are no parameters, so schema coverage is effectively 100% and the description has nothing to add about parameter meaning. The baseline of 4 for a parameterless tool is appropriate; the description correctly focuses on behavior and output rather than inputs.

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 ("The user's Renderball documents") and adds useful output details: newest first, with editor links. The title supplies the explicit "list" verb, and this is distinguishable from siblings like see_deck because it refers to the full set of decks rather than a single one.

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 an important precondition ("Needs an account (a key)") and implies use whenever the user wants their own decks in reverse chronological order. It does not explicitly state when to use this tool over siblings or when not to use it, so the guidance is context only, not exclusionary.

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

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

Beyond the readOnlyHint annotation, the description adds that the output is a set of page images in order, and that it exposes rendering quality issues. It also discloses the availability precondition. This is useful behavioral context, though it does not detail response format or page-count behavior.

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

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

The description is a single substantive sentence followed by a necessary availability condition. Every clause earns its place, and the inspection-purpose is front-loaded before the workflow instruction.

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

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

For a simple 2-parameter, read-only visual inspection tool, the description gives the output type, ordering, the availability gate, and the recommended follow-up action. It lacks explicit return-value details, but the absence of an output schema makes the current level mostly sufficient.

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 50%, with guest_token documented but deck_id not. The tool description provides no additional meaning for either parameter, such as clarifying that deck_id must refer to a submitted deck. The precondition indirectly implies which deck to pass, but that is not enough to compensate for the 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?

The description states a clear verb and resource: the tool returns the deck's rendered pages as images, page 1 first. It also frames the purpose as visual QA (checking overlap, clipping, spacing), which distinguishes it from sibling tools like submit_deck and create_deck.

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 says the tool is 'available once the deck has been submitted' and prescribes a follow-up workflow: inspect the images, fix the file, then call submit_deck again. It does not explicitly list when not to use it, but the precondition and workflow give clear enough context.

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

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

Annotations already signal that this is a mutating but non-destructive operation; the description adds that it enables public-link visibility, which is useful privacy context. However, it does not disclose whether the link can be revoked, whether ownership permissions are required, or what the return value contains, so it only partially expands beyond the annotations.

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

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

One short, front-loaded sentence conveys the action before any details. There is no filler, and every word contributes to either the purpose or the expected outcome.

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 phrase 'return it' is ambiguous; an agent cannot tell whether the result is the public link, the deck object, or a status. The guest_token condition is already covered by the schema, so the main missing piece is a clear return contract.

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 description does not explain deck_id or guest_token; only the schema describes guest_token and places constraints on deck_id. With schema description coverage at 50%, the description should compensate for parameter semantics but does not, leaving the agent to infer meaning from parameter names.

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 phrase, 'Turn on the public link for a deck,' naming both the action and the resource. This makes share_deck's job unambiguous and distinguishes it from sibling tools like see_deck and deck_status.

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

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

The description implies the tool is for making a deck publicly accessible via a link, but it never explicitly states when to prefer share_deck over alternatives or when not to use it. The guest_token condition is documented in the schema, not in the description, so no direct tool-selection guidance is provided.

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 are minimal (readOnlyHint: false, destructiveHint: false), so the description carries the full behavioral burden and delivers: validation of the deck against the brief, automatic repair of small slips, rendering, opening in the editor, and the two return states (ready with editor_url, or importing). This exposes side effects and asynchronous behavior that the structured fields do not.

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

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

Three sentences, each earning its place: the action, the processing pipeline, and the return contract. The core verb is front-loaded ('Send the complete deck file you wrote') before behavioral details, and there is zero filler or repetition of schema content.

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 5-parameter, no-output-schema, asynchronous tool, the description covers the main workflow and return contract, and correctly points to deck_status for polling. It does not disclose failure/error behavior (e.g., what happens if the deck badly fails the brief check) and leaves 'repairs small slips' vague, but the essential invocation and post-call flow are sufficiently explained.

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 80% (only deck_id lacks a description), setting the baseline at 3. The description adds some value beyond the schema—tying 'the complete deck file you wrote' to source and implying the brief-compliance constraint of source—but it does not clarify deck_id, label, guest_token, or the wait_seconds/importing relationship beyond what the schema already states.

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+resource ('Send the complete deck file') and then differentiates itself through a unique pipeline: checks against the brief, repairs slips, renders every page, opens in the editor, and returns ready/importing states. None of the siblings (create_deck, write_outline, deck_status, see_deck) claim this submit-and-import behavior, so an agent can distinguish it without opening schemas.

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 clear usage context ('Send the complete deck file you wrote', 'checks it against the brief') implying the tool is used after authoring and after a brief exists. It also explicitly routes to the sibling deck_status with 'then poll deck_status' for the importing case. It lacks explicit when-not-to-use exclusions (e.g., don't call it before create_deck, or before the deck is complete), so it falls just short of the 5 bar.

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 indicate this is a non-read-only, non-destructive operation. The description adds that the tool returns a WRITING BRIEF and instructs the agent to follow it, which is useful. However, it does not disclose side effects (e.g., whether repeated calls overwrite the outline), authentication requirements, or failure behavior. It is consistent with annotations.

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

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

Three crisp sentences: action first, return value second, next step third. No redundant phrases; every sentence earns its place.

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

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

The description explains the return value and next step, which is important given no output schema. But it omits prerequisites (must have a valid deck_id from create_deck, or guest_token for anonymous decks) and any error conditions, leaving the agent to infer the workflow from sibling tool names. For a tool with a complex pages schema and no output schema, this is a noticeable 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?

Schema description coverage is 50%, and the description does not compensate. It adds minimal meaning only for pages ('page-by-page') and deck ('for a deck'), while saying nothing about the optional tone or guest_token parameters, both of which lack clear semantics in the description. The two required parameters (deck_id, pages) have no top-level schema descriptions, and the description does not clarify them.

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

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

States a specific verb ('Save') and resource ('page-by-page outline for a deck'), and clarifies it returns the WRITING BRIEF. It distinguishes from sibling submit_deck by explicitly positioning it as the step before submission, and from create_deck by focusing on saving an existing outline.

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 clear workflow context: save the outline, get the WRITING BRIEF, follow it, then call submit_deck. It names the next sibling explicitly, but does not state exclusions or alternatives (e.g., when to use get_brief instead) or prerequisites like having called create_deck first.

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