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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds the crucial reason: an existing grant is replaced, and that replacement can lower the recipient's access. That is real value beyond the structured fields and directly explains the destructive flag. It stops short of covering required permissions or whether the recipient is notified.

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 zero filler: the action and its scope come first, and the destructive edge case follows as a warning. 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 an output schema present, the description needn't describe return values, and annotations cover mutability and openness; the description closes the remaining behavioral gap by explaining the role-replacement effect. It is slightly thin on prerequisites and on how it differs from 'share_deck', which keeps it from a 5.

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 67%, and the schema already documents 'subject' (user id or email creating an EMAIL grant) and 'role' (access level enum). The description reinforces that subject accepts an ID or email and adds that only a single subject is accepted, but contributes nothing for the undocumented 'deck_id'. Baseline 3 is appropriate given the schema does most of the work.

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 ('Share a deck'), scoped to exactly one recipient ('one person, by user ID or email address') at a specified role, so an agent knows precisely what the call does. However, it never distinguishes itself from the sibling tool 'share_deck', so the agent must guess which of the two performs which sharing operation.

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 phrase 'one person' suggests this is the single-recipient path versus some broader sharing path, but no alternative is named and no preconditions (ownership/admin rights on the deck) are stated. The caveat about replacing an existing role is genuinely useful context, but it describes an effect rather than when to choose this 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?

Strong disclosure beyond the annotations: statelessness (nothing persisted), the 10-credits-per-slide charge taken once before return, a 402 on empty balance, and 409 semantics for reused idempotency keys. The retry-safety note is consistent with idempotentHint=false, and nothing contradicts destructiveHint=true, though the description never explains what the destructive flag actually refers to for a tool that persists nothing.

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 paragraphs, purpose front-loaded, then prerequisites, then billing/retry. Every sentence carries distinct operational information (persistence, extraction readiness, price, error codes) with no filler.

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?

Return values are covered by the existing output schema, and the description supplies the side-effect, cost and retry facts an agent needs before calling. The only gap is the accept-language header parameter, which is undocumented in both schema and description.

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?

With 71% schema coverage, the schema already documents prompt, sources, language, slide_count and level_of_detail in detail. The description adds genuine meaning only for the undocumented Idempotency-Key (retry safety, 409 on a key that already paid); accept-language gets no explanation anywhere, so it neither fully compensates nor adds much beyond the 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?

The description states a specific verb and resource ("Generate a stateless outline") plus its input modes (prompt and/or extracted files), and the word "stateless" plus "No deck... is persisted" cleanly separates it from the create_presentation sibling. An agent can tell what this produces without opening the 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?

It gives real entry conditions (referenced files must be in the caller's workspace and already extracted) but never names an alternative sibling or states when to pick create_presentation versus create_outline, leaving the main routing decision to inference. Prerequisites are covered; exclusions are not.

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 annotations it discloses that generation is asynchronous (a few minutes, poll task_id), consumes credits, saves into the workspace, and that an identical retry returns the same deck while a new request_id makes another copy — all non-obvious and not in the structured fields. It does not explain failure handling or what a spent-credit failed run leaves behind, so the mutation lifecycle is only partly 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?

Front-loaded with purpose and trigger, then input construction, then the asynchronous follow-up path — a sensible order for a complex tool. A few parentheticals (e.g. the sources example object) are borderline redundant with the 100%-covered schema, but nothing is wasted enough to hurt.

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 tool with 20+ nested deck fields, no output-schema explanation is needed, and the description instead supplies the piece an agent actually needs: the generate-then-poll-then-export/share workflow. Combined with the full schema coverage, an agent has enough to call it correctly and handle the result.

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; the description adds real routing value by pointing brand_kit_id at search_brand_kits and outline at create_outline's output, and by enumerating representative deck fields (prompt, sources, slide_count, audience, level_of_detail, deck_purpose). It stops short of explaining the outline-vs-prompt mutual exclusivity enforced by the oneOf, which the agent must infer from 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 first sentence gives a specific verb and resource with scope: 'Create a finished, designed presentation from a prompt, text, or an outline.' The second sentence lists the user phrasings that should trigger it (presentation, deck, slides, pitch, PowerPoint), which separates it cleanly from create_outline (outline only) and get_deck (retrieval).

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?

Explicit trigger language ('Use it when the user asks for...') plus routing to siblings: create_outline for the outline input, search_brand_kits for brand_kit_id, get_task/get_export/share_deck for the post-generation steps. The user's request for a public link is named as the condition that selects share_deck.

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 restating idempotency adds little. The one genuine addition is 'soft-delete', which tells the agent data is not physically purged, but the description leaves out whether the deck becomes inaccessible, whether shares/grants cascade, and whether there is any undo path.

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 short sentence, front-loaded with the operative term 'soft-delete'. The second clause repeats the idempotentHint annotation, so it is slightly wasteful but harmless.

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 destructive mutation with no output schema, the description covers the core action but omits consequences an agent should know before calling: effect on existing shares/grants, whether the deck disappears from list_decks, and recoverability. Annotations carry the safety profile, so this is adequate 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 description coverage is 0%, but the single parameter is a self-describing UUID deck_id whose type and format are already declared in the schema. The description adds no meaning about accepted identifier forms or behavior on unknown IDs, so it neither compensates nor misleads.

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+resource ('Soft-delete a deck'), and 'soft' meaningfully distinguishes it from a hard delete or from patch_deck in the sibling list. It does not explicitly name a sibling it should be preferred over, which keeps it from a 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?

There is no when-to-use guidance: nothing says when to delete versus patch_deck, whether deletion is reversible by the user, or what preconditions apply. The only usage-adjacent information is that repeat calls on an already-deleted deck are safe.

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 readOnly, idempotent, non-destructive, and closed-world, so the description's added value is the export-URL caveat: download links open without a key and expire in 15 minutes. That is a genuine operational fact an agent could not obtain from the structured fields.

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 filler, with the returned payload listed first and the expiry caveat second. 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?

An output schema exists, so return-value detail is not required, and the tool is simple (one required id, read-only). The description still covers the payload and the URL expiry, leaving only minor gaps such as behavior when the deck_id does not exist.

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

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

Only one parameter, deck_id, with 0% schema description coverage, but its name and uuid format make it self-explanatory. The description adds nothing about the identifier's source (e.g. from list_decks), so it sits at an adequate baseline rather than excelling.

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 specific verb ('Fetch') and the exact payload: deck metadata, latest generation status, and export artifacts. That distinguishes it from list_decks (enumeration), get_task, and get_export, though it never explicitly contrasts itself with 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 statement of when to call this versus get_export, get_task, or list_decks, and no preconditions. Usage is only inferable from the required deck_id and the payload description.

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/destructiveHint/openWorldHint annotations already establish that this is a safe, closed-world read. The description does add one genuinely useful operational fact, that the download URL is short-lived, which an agent must know to use it promptly. It does not say whether a missing export yields an error or an empty result, which is the main remaining 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?

A single front-loaded sentence with no wasted words; the essential facts (latest artifact, download URL) come first. It is a sentence fragment rather than a full clause, which slightly weakens readability but does not obscure meaning.

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 document return fields, and annotations cover the safety profile. For a simple single-parameter read, the remaining gap is the no-export/pending-export case and URL expiry timing, which would materially change how an agent sequences its calls.

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 parameter, deck_id, and schema description coverage is 0%, so the schema itself says nothing about it. The description implies deck_id identifies the deck whose export is wanted, which is marginal added meaning beyond the name, but does not clarify format expectations, error behavior for unknown IDs, or export scope (slides vs. assets).

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 resource and scope: the latest export artifact for a single deck, plus the fact that a download URL comes back. It does not use an explicit verb ('retrieve'/'fetch') and does not name a sibling, but no sibling in the list deals with exports, so an agent can still distinguish it easily.

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 guidance on when to call this versus other tools, and no mention of what to do if the deck has not been exported or an export is still in progress. The agent must infer both the trigger condition and the fallback behavior.

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, and the description adds real behavioral detail on top: the call can block, the wait is capped at 60s, and it terminates early on COMPLETED/FAILED. It does not enumerate the full status vocabulary or say what happens if the task_id is unknown/expired, which are the remaining behavioral gaps.

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 what the tool returns, then the wait_time semantics, then the handoff to get_export. Nothing is redundant with the schema or annotations, and every sentence 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?

An output schema exists, so return values need no prose, and the polling/blocking model plus the get_export handoff cover the core of a two-parameter read tool. The only shortfall is not stating the provenance of task_id or the full set of terminal/non-terminal statuses an agent might branch on.

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 both parameters. It does this well for wait_time (0 vs >0, 60s cap, terminal-state early exit), but task_id is never explained — no statement of where it comes from or its lifetime. Half the parameters are covered, so this lands at adequate rather than strong.

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: retrieves the status of an async task, with a concrete example (presentation generation). It also names the natural follow-up tool, get_export, so an agent can place it among siblings like get_deck and get_export 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 branching guidance: wait_time=0 for an immediate snapshot, wait_time>0 to block until COMPLETED/FAILED or the window elapses, and points at get_export once a generation is COMPLETED. It stops short of saying when to prefer polling versus waiting in a given workflow, and never says where task_id originates (presumably create_presentation).

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 readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds a genuinely non-obvious behavior beyond them: decks whose generation is still running or never completed are silently omitted from results, which would otherwise look like missing data.

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 filler. The core capability comes first and the exclusion caveat follows immediately where it is most useful.

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 unnecessary, and the key trap (empty decks omitted) is disclosed. Minor gaps remain around pagination result shape and what the search string matches, but nothing that would cause an incorrect call.

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 17%, so the description has to carry weight; it names the filter categories (project, flag, sort, search, pagination) which map onto project_id, flag, sort, search, page, and limit. It adds no detail on search matching semantics, flag values, or sort ordering beyond what the schema enums already state, so it only partially compensates.

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 accessible decks") and enumerates the filter dimensions (project, flag, sort, search, pagination). The closing clause routes the agent to the id-based sibling (get_deck), so it is distinguishable from siblings without opening a 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 a concrete usage rule: decks with no slides are excluded from this listing and must be fetched by id instead. That is a real when-to-use/when-not-to-use distinction, though it does not cover choices against other list-style siblings such as list_projects.

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 readOnly, idempotent, non-destructive, so the safety profile is covered; the description adds genuinely non-obvious access semantics instead — that a project-bound key sees only its project and descendant folders, and that 'top level' includes parents the caller cannot reach. That visibility/auth scoping is real behavioral context beyond the structured fields.

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?

Dense and front-loaded: the listing mode comes first, then the top-level rule, then the permission scope. Minor friction from mid-sentence line breaks that split 'parent they / cannot reach' and 'folders below it, / with that project as its top', but no sentence 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?

An output schema exists, so return-value detail is rightly omitted, and the access-scoping notes cover the trickiest behavior. Still, for a 5-parameter listing tool at 20% schema coverage, the absence of any pagination guidance (`page`/`limit` defaults and the 200 cap) leaves a gap an agent could stumble on.

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 20% (only `kind` is documented), so the description must compensate — and it partly does, explaining `kind=FOLDER`, `parent_id` as 'one container's children', and `top_level` semantics plus its conflict with `parent_id`. However, `page` and `limit` get no mention, leaving two of five parameters undefined in both places.

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?

Opens with a specific verb+resource ('List projects') and immediately clarifies the dual mode via `kind=FOLDER`. It also scopes the listing to 'optionally one container's children', so an agent knows this is a filtered enumerator rather than a global dump. It does not name a sibling to contrast with (e.g. list_decks), which keeps it from a 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?

Gives an explicit incompatibility rule: 'Not with `parent_id`' when `top_level=true`, which is exactly the kind of when-not guidance agents need. It also defines what `top_level=true` preserves. It stops short of stating when to prefer this over other listing tools, but the constraint guidance 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?

Annotations already flag destructiveHint=true and idempotentHint=true, so the safety profile is partly covered; the description adds real value by spelling out the concrete consequence — changing visibility can make the deck public or strip other people's access. It does not mention the share-manage permission requirement, which lives only in the schema, but the material risk is disclosed in prose.

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 primary operations before the caveats. The middle sentence about switching content version could have been folded into the opening list, but there is no filler or repetition.

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 annotations covering safety, a rich schema, and an output schema to describe returns, the description only needs to establish scope and risk. It does both: it enumerates all four patchable dimensions and warns about the visibility side effect, leaving nothing an agent needs before calling 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 80%, so the baseline is 3. The description names every optional parameter's effect at a high level (rename, visibility, project move, version switch) but adds no semantics beyond what the schema already states, such as the constraint that version must be one the deck has content for.

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 leads with specific verbs and the resource: rename a deck, change who can open it, move it to another project, and switch the rendered content version. It distinguishes itself from create_presentation and get_export through explicit negatives ('doesn't start generation or create an export'), though it never clarifies its boundary against the sibling share_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?

Usage is implied by the operation list plus the exclusions ('doesn't start generation or create an export'), which tells the agent what this tool is not for. However, no alternative is named for the overlapping case — an agent wanting to grant access could plausibly pick either this tool or share_deck, and the description offers no rule to choose.

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 readOnly, idempotent, non-destructive, closed-world, so safety needs no restating. The description adds genuinely non-obvious visibility semantics: published catalog brands, workspace kits, and the caller's own unshared kits are all returned, and domain-restricted brands appear only when the verified email domain matches. That is real behavioral context an agent could not infer from the schema.

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 purpose, followed by integration and visibility rules. No filler or repetition of annotation data.

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-shape explanation is correctly omitted, and the description covers the two things an agent could not derive elsewhere: visibility rules and id reuse. The remaining gap is parameter-level guidance for filtering and paging in a tool that returns up to 100 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?

Five parameters, 60% schema description coverage, and the description says nothing about `q`, `page`, `limit`, `type`, or `domain` semantics. Its mention of approved email domains concerns result visibility, not the `domain` filter parameter, and the `type` enum values (CATALOG/WORKSPACE/PERSONAL) go unmentioned despite being the main way to narrow scope.

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 opens with a specific verb and resource ('Search the brand kits you can style a deck with') and immediately narrows the scope to kits usable for deck styling. It does not need to distinguish itself from a competing brand-kit sibling because none exist in the sibling list, so it lands just short of the top mark.

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 concrete follow-on usage: take a result's `id` and pass it as `brand_kit_id` when creating a deck, which tells the agent how this tool chains into `create_presentation`. It stops short of explicit when-not-to-use guidance or stating that pagination/filters should be used to narrow large result sets.

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?

Goes well beyond the annotations by disclosing the access model ('anyone with the link can open the deck'), the idempotent behavior ('reuses the existing link so the URL is stable'), and the destructive consequence of rotate ('the previous URL stops working'). That last point concretely explains where the destructiveHint=true applies, which the annotation alone leaves ambiguous.

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 what the tool does, then the safety constraint, then the parameter behavior. 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?

Covers purpose, access implications, reuse semantics, and the destructive rotate path; an output schema exists so return-value detail need not be spelled out beyond the URL mention. Nothing needed to invoke it 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 0%, so the description carries the burden: it fully defines rotate's semantics, default behavior, and side effect, which the bare boolean type could not convey. deck_id is left to the schema's uuid format and name, which is reasonable since its meaning is self-evident from the purpose sentence.

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 pair ('Get or create the deck's public share link') and the return value ('return the URL'). No sibling tool in the list does sharing, so it is unambiguously distinguishable from get_deck, patch_deck, or create_grant.

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 constrains usage: 'use it only when the user asks for a link or to share the deck,' which is a real exclusion rather than a vague hint. It also explains when to pass rotate=true. It does not name a competing tool, but none exists among the siblings, so the only gap is minor.

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 readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is fully covered. The description usefully adds that the result spans identity plus plan and credit balance, but says nothing about auth assumptions or what happens if no account is connected.

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, no filler. The what-it-returns statement comes first and the when-to-use guidance second, which is the correct front-loading for a zero-arg tool.

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 structure need not be explained. For a zero-parameter, read-only identity call with full annotation coverage, the description supplies everything an agent needs to decide and invoke.

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 there is nothing for the description to disambiguate; baseline 4 applies. The enumeration of returned fields gives a hint of what the call surfaces without needing input 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?

States a specific resource (the connected account) and enumerates exactly what is reported: email, workspace, role, plan, credit balance. None of the sibling tools (deck/project/task/brand-kit management) overlap with this identity lookup, so an agent can select it unambiguously.

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 second sentence gives clear triggering conditions: when the user asks which account is connected, what plan they're on, or how many credits remain. It does not name an alternative, but no sibling offers account or billing information, so there is little ambiguity to resolve.

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