Capxule

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real behavioral context beyond that: results are paginated cards identical in shape to find_journey output, accompanied by a total and a next_offset for continuation. Missing only details like ordering or empty-result 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?

Two tight sentences with the usage trigger front-loaded, followed by the return-shape contract. No filler, no repetition of the title, and every clause carries information the 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 no output schema, the description still specifies what comes back (a page of journey cards, a total, a next_offset), and the optional category path is fully explained. Nothing required to call or continue pagination correctly is absent.

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

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

Schema coverage is 100%, so limit, offset and category are all documented with ranges, defaults and the next_offset chaining rule. The description reinforces only the category-to-list_journey_categories relationship and says nothing about limit or offset, so it adds little beyond the schema baseline.

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

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

States a specific verb and resource ('look through the journeys') with an explicit scope modifier (optionally one category), and contrasts it with the search-oriented sibling find_journey and the source of category slugs, list_journey_categories. An agent can distinguish this browse/list tool from the other eight siblings 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?

'Use when the user wants to look through the journeys' gives a clear trigger condition, and the parenthetical explains the one optional filter and where its values come from. It does not state an explicit when-not or name the exact condition that would select find_journey instead, so it falls short of full routing 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?

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the description adds real value by disclosing the account-gating behavior and the exact failure sentinel 'not_available'. It does not say whether the takeaway is persisted server-side or merely returned, which is the one behavioral detail still missing for a create-verb 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?

Three sentences of roughly equal weight: trigger first, then what is produced, then availability. No restatement of the title and 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?

For a 3-parameter tool with no output schema, the description covers the trigger, the output format and the failure mode. The only substantive hole is the undocumented 'kind' enum branching, which is what an agent most needs before calling with kind='template'.

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 67% and the uncovered parameter is the important one: the 'kind' enum ('takeaway' vs 'template') has no description and the description never explains which value to choose or that 'template' changes the required inputs. The 'session' and 'template_id' semantics are already documented in the schema, so the description adds almost nothing there.

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 and artifact: 'Composes a markdown takeaway from this journey session', followed by the exact contents (what the user asked, key points, stops visited). That is far more concrete than the sibling names imply and none of the siblings produce a takeaway. It stops short of naming an alternative tool, so it is clear but not sibling-differentiating.

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?

'Use when the user asks for a summary to keep' gives an explicit trigger condition, and the connected-account caveat tells the agent when the call will fail. There is no statement of when NOT to use it, e.g. for a running progress check, which would have earned a 5.

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

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

Annotations only cover safety (readOnly, non-destructive, closed-world); the description goes well beyond them by disclosing the result cap (three cards), the exact fields returned, the meaning of `in_progress: true`, and the `alternatives` fallback when nothing matches. That is exactly the behavioral context annotations cannot supply.

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

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

Front-loaded with the usage condition, then the return shape and edge cases. The field enumeration is dense but each item (shape, languages, stops, minutes, who it is for/not for, premium, page_url) earns its place since no output schema exists.

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

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

With no output schema and readOnly-only annotations, the description fully carries the return-value burden: card fields, the in_progress marker, and the no-match `alternatives` behavior. Nothing an agent needs to interpret results or call correctly is missing.

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

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

Schema description coverage is 100%, so query, limit (1-3) and locale enum are already documented in the schema. The description adds no parameter-level detail such as query phrasing or locale behavior, so the baseline 3 applies.

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

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

States a specific verb (searches) and resource (published journeys) with the scope 'guided, step-by-step journey on a topic, a skill or an exam'. It implicitly separates itself from browse_journeys by being a query-driven search rather than a browse, but no sibling is named explicitly.

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

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

'Use when the user wants a guided, step-by-step journey on a topic, a skill or an exam' gives a clear triggering condition. There are no explicit when-not conditions or named alternatives (e.g. browse_journeys, list_journey_categories), so an agent must infer the boundary.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine value beyond that by enumerating the returned payload (current stop, visited/remaining stops, percent done, practice stats, limits, resume line), which matters because there is no output 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?

Two sentences, zero waste, with the trigger condition front-loaded and the return contents following. Every clause 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?

With one parameter, no output schema and full annotation coverage, the description is nearly complete for a safe read tool, and it compensates for the missing output schema by listing return fields. It omits edge-case behavior, such as what happens with an expired or invalid session handle.

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

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

Schema coverage is 100% and the single parameter is fully documented, including provenance ('from open_journey') and the cxs_ prefix. The description adds no parameter guidance at all, so the baseline 3 applies.

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

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

States a specific verb+resource ('get journey progress') and adds a user-intent framing ('where they are in a journey, how far they have come or how much is left') plus an enumeration of returned data. It does not explicitly distinguish itself from get_resume_link or open_journey, though the 'resume line' mention hints at overlap.

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 clear trigger conditions tied to user phrasing ('Use when the user asks where they are...'), which is directly actionable. It stops short of naming exclusions or pointing to alternatives such as get_resume_link for a shareable link.

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 declare a non-read-only, non-destructive, closed-world call, and the description adds meaningful context beyond that: the output is two artifacts (link plus short resume code) bound to the current session. It does not mention expiry, reuse limits, or whether the link is single-use, which would matter for a generated credential.

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

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

Two sentences, zero filler. The usage condition leads and the return contract follows, which is the right front-loading for a one-parameter 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?

With no output schema, the description correctly carries the return-value burden by naming both returned artifacts. It leaves out link lifetime and what happens to the session after resuming elsewhere, minor gaps for a tool this simple.

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

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

Schema coverage is 100% and the single 'session' parameter is fully documented there, including the cxs_ prefix hint. The description's 'for this session' reinforces the scoping but adds no new mechanics, so the baseline of 3 applies.

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

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

States a specific outcome: it returns a resume link and a short resume code tied to this session. The verb is implied rather than stated, and it doesn't explicitly contrast with siblings like open_journey or get_journey_progress, but the return artifact makes the tool's identity 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?

Gives a clear trigger condition: 'when the user wants to continue the journey later, on the website or in another assistant.' That is a strong situational cue. It stops short of naming an alternative or an exclusion case, so it doesn't reach the explicit when/when-not 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 declare readOnly, non-destructive, closed-world, so the safety profile is covered. The description still adds value by disclosing the exact payload of each item (slug, readable label, journey count, example titles), which tells the agent what it can do with the result. No pagination or size limits are mentioned, but with zero parameters and a bounded category set that 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?

Two sentences, zero waste: the usage trigger comes first, then the return shape. Every clause earns its place and nothing is repeated from the schema or annotations.

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 parameters, no output schema, and lightweight annotations, the description carries exactly the information an agent needs: when to call it and what it gets back. There is no meaningful omission for a tool of this 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?

The tool takes no parameters, so there is nothing for the description to disambiguate; baseline for a zero-parameter schema applies. The description correctly implies a single no-argument call.

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 (list) and resource (journey categories) and immediately clarifies that the unit returned is a category, not a journey — which separates it from browse_journeys and find_journey. It stops short of naming a sibling, so it is clear but not maximally differentiated.

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?

Opens with an explicit trigger: 'Use when the user asks what kinds of journeys are available.' That gives a concrete invocation condition. It does not state when not to use it or point to browse_journeys for the follow-up step, so it falls short of a 5.

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

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

Annotations already declare non-read-only, non-destructive, closed-world behavior, and the description adds important semantics: repeated calls resume the same session rather than resetting progress, and it enumerates the returned session contract. This is exactly the kind of stateful behavior an agent needs 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?

Three sentences, front-loaded with the usage condition, then behavior, then idempotency and return contract. 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?

With full schema coverage, annotations covering safety, and an explicit description of the return contract, the definition is complete enough to call correctly. No output schema is present, but the description compensates by naming returned fields.

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 schema already documents all five parameters including enums and bounds. The description adds no parameter-level detail beyond the general resume concept, so 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 names a specific action (open/resume) and resource (journey), and explicitly covers both starting and continuing. It adds scope detail ('never resets progress') that helps distinguish it from restart_journey.

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 a clear triggering condition ('when the user chooses a journey to start or continue') and mentions resume via get_resume_link only in the schema. It does not explicitly name sibling alternatives such as find_journey, browse_journeys, or restart_journey, so it stops short of full when/when-not 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?

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds the exact scope of destruction: visited stops are cleared while already-used turns stay used. That 'what survives vs what is lost' detail is precisely the context annotations cannot convey, and it is not contradicted anywhere.

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 safety gate ('use only when... after confirming') before the state effects and the return contract. No filler and no repetition of the 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?

No output schema exists, and the return value is described only by reference ('same session contract as open_journey'), which assumes the agent knows that sibling's shape. Everything else an agent needs for a destructive reset is present, so the gap is minor but real.

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 slug, locale and capsule_id are already documented with their roles and a locale enum. The description adds no additional parameter semantics such as the slug-vs-id precedence, so the baseline 3 applies.

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

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

States a specific verb and resource ('restart a journey') and immediately defines the mechanics: returns to the first step and clears visited stops. This clearly distinguishes it from open_journey (fresh start) and take_journey_step (advance), so an agent can route correctly 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 an explicit gating condition ('Use only when the user explicitly asks to start a journey over') plus a required prerequisite ('after confirming with them'). The implicit alternative for a non-reset start is open_journey, which is named in the return-contract sentence.

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

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

Annotations already establish non-read-only, non-destructive, closed-world behavior. The description adds meaningful behavior beyond that: fresh turn_id per step, idempotent replay returning the stored step, and the instruction to surface wall.for_human when present. It could say more about what state is mutated, but the idempotency and wall handling are substantive.

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?

It is compact, front-loaded with the primary usage rule, and every sentence contributes: usage, return shape, action selection, idempotency, and wall handling. 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?

For a complex multi-action tool with no output schema, the description covers the main flow, return fields, idempotency, and special wall handling. The only notable omission is explaining when or why to use the resume action, which leaves that branch incomplete.

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 description meaningfully clarifies action semantics beyond the schema: pick versus say conditions, go targeting a contract stop, and drill/simulate/exit contexts. It still omits the resume action entirely, so one action variant is left for the schema alone to define.

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 (take_journey_step) and immediately scopes it to 'every step after open_journey', distinguishing it from the sibling open_journey tool. It also says what the tool returns: the next step with answer/statement/options/media/progress/limits.

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 clear selection rules: use after open_journey; send pick when the user chose an option or number, otherwise send say. It also explains go, drill, simulate, and exit action contexts, though it never mentions the resume action, leaving that branch undocumented.

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