humanitix

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

Annotations already declare destructiveHint=true, so the mutation risk is conveyed structurally. The description adds value by disclosing the return content (scanning messages) and the undo path, but says nothing about permissions, duplicate-scan behavior, or rate limits that matter for a door-scanning mutation.

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 action, then return behavior, then the inverse tool and endpoint. No filler; 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?

Low-complexity two-required-param mutation with no output schema, and the description covers the action, the return payload, and the undo route. The remaining gap is behavioral edge cases (duplicate check-ins, failure modes), which is minor for this tool shape.

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%, including the hex-id format guidance and the region enum, so the schema carries parameter meaning. The description adds only the endpoint template, which implies event/ticket ids but offers no syntax or format detail 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?

Specific verb+resource ('Mark a ticket as checked in at the door') plus the side effect of returning scanning messages. It explicitly names the inverse sibling humanitix_check_out_ticket, so an agent can distinguish it from the check-out tool without opening either 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?

States the context ('at the door') and names the alternative for reversing the action ('Undo with humanitix_check_out_ticket'), which routes the agent correctly. It stops short of broader when-not-to-use guidance (e.g. already-checked-in tickets, duplicate scans), so it is clear context without full exclusions.

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, so the safety profile is covered. The description adds one useful behavioral fact beyond that — the ticket must already be checked in — but says nothing about idempotency, whether an already-checked-out ticket errors, or regional/auth implications of the mutation.

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 for purpose plus the endpoint mapping, with zero filler. The effect and the exception cases come before the API path.

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 two-required-parameter state-mutation tool with no output schema, the description covers purpose, precondition and effect, and annotations supply the destructive flag. Only error/edge-case behavior at the boundary (double check-out, unknown ticket) is left unstated.

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%, including the 24-char hex patterns and the region enum explanation, so the schema carries the parameter burden. The description adds no parameter-level syntax or format detail, making the baseline 3 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?

States a precise verb+resource ("Mark a checked-in ticket as checked out"), names the source state, and gives concrete use cases (undo a mistaken check-in, track re-entry). An agent can distinguish this from the inverse sibling humanitix_check_in_ticket without opening either 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?

The parenthetical "e.g. to undo a mistaken check-in or track re-entry" tells the agent when this tool is the right choice rather than check-in. It stops short of explicitly naming the alternative tool or stating a when-not condition, so it is clear context without 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 carry only destructiveHint=true, so the description carries most of the load and does so well: it discloses the 403 permission prerequisite and that ticket types are set up elsewhere, and cites the underlying endpoint. It stops short of describing idempotency or what the created event identifier looks like, which for a mutation tool would be valuable.

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 tightly packed sentences: the creation scope first, then the permission caveat and workflow note, then the endpoint reference. Nothing is padding and the key constraint (403 without permission) is not buried.

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

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

For an 8-parameter tool with nested location/classification objects and no output schema, the description covers scope, the permission blocker, and the multi-step workflow. It leaves the return shape and the event ID implied, but the schema and the 'base event' framing give the agent enough to invoke correctly.

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 every one of the 8 parameters is already documented in the schema with formats and enums. The description only restates the field list at a high level, adding no format, default, or constraint details beyond the schema. 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?

States a specific verb and resource ('Create a base event') and enumerates the fields the base event carries, plus clarifies what is NOT created (ticket types, handled in the console). This differentiates it well from the ticket/order siblings. It does not explicitly name update_event or get_event as the alternatives, so it stops short of 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?

The description gives one concrete usage condition – a special Humanitix permission must be enabled or the call returns 403 – which is genuinely actionable. However, there is no guidance on when to create vs. update an existing event, no ordering advice relative to the ticket-type workflow, and no exclusions.

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 destructiveHint annotation already marks it as a mutation, but the description adds essential traits: partial-update semantics, a special permission requirement with 403 consequences, inability to delete dates, and the underlying PATCH endpoint. This gives the agent operational context beyond what annotations provide.

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

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

Four tight sentences, each earning its place. Key partial-update semantics and date-operation scope are front-loaded before the permission requirement and endpoint reference.

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 nested-parameter mutation tool, the description covers the highest-risk gaps: partial updates, authentication/permission requirements, date operation constraints, and endpoint. With no output schema, it correctly focuses on behavioral and usage context rather than return values.

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 baseline is 3. The description still adds value by clarifying that only passed fields are sent and by explicitly stating that date deletion is not exposed, a constraint not spelled out in the schema's oneOf structure.

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 (update) and resource (an event), then enumerates the exact updatable fields. The action is clearly distinguishable from sibling tools like create_event, get_event, and list_events 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 clear context: it is a partial PATCH that only sends passed fields, requires special account permission, and supports CREATE/UPDATE date operations but not deletion. It does not explicitly name alternative tools (e.g., create_event) or when-not-to-use conditions, so it stops just 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.