Zovo Shared Checklist

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

Annotations already declare the mutation and open-world profile, and the description adds real substance on top: the page is published publicly, two distinct links are returned with different audiences, there is a 64 KB text budget, and no notifications are sent. It stops short of stating auth or permission requirements and doesn't say what happens if the same checklist is created twice (relevant given idempotentHint=false).

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 use case, then behavior and return values, then limits, then the exclusion, so an agent can stop reading at any point and still act correctly. No filler and no repetition of the title or schema.

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 trigger, side effects, capacity limits, locale-sensitive sizing, and the negative case, which is everything needed for a non-idempotent create tool. Return values are described briefly and an output schema exists, so no further detail is owed there.

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, but the description adds meaning the schema cannot express: the 64 KB total-text ceiling and its practical item counts per language, plus the fact that due dates are validated against the supplied time zone. The rest (item count range, optional section/assignee/due) largely restates schema constraints.

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 ('Publishes a page') plus the concrete output ('a public link to share and a private organizer link'), which no sibling provides. The create-versus-update split against update_shared_checklist and show_checklist_results is unambiguous from the operation described.

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 when-to-use trigger with four concrete scenarios (moving house, wedding prep, event setup, onboarding) and an explicit when-not ('Do not use for a private to-do list nobody else needs to see'). It also rules out an expected capability ('Does not send reminders or notifications'), which prevents a misfire.

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 and non-destructive, so the safety profile is covered; the description adds the access-control requirement (a private organizer link is mandatory) and the timezone semantics for overdue/due-today items. These are real behavioral facts beyond the structured fields, with only return format left implicit.

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 use case before the mechanics, and no filler sentences. It runs slightly long as a dense paragraph, but each clause (trigger, prerequisite, return contents, side-effect disclaimer) contributes distinct information.

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

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

For a one-parameter read tool with an output schema and full annotation coverage, the description covers when to call, what is required, and what is returned at a high level. Nothing essential is missing, though scale behavior for very large checklists is unmentioned.

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 already documented with a format example, so the schema carries the load. The description reinforces that the link is private and mandatory, but adds no new syntax or format detail beyond that framing.

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 read operation ('returns progress by section and by person') on a named resource, and anchors it to the sibling that creates the checklist ('made with create_shared_checklist'). The agent can distinguish this read tool from create/update 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 explicit trigger conditions ('when the organizer asks how far along... what is overdue, who did what, or what is left') plus a hard prerequisite ('Do not use without the organizer link'). It signals the boundary by stating it does not change the checklist, though it never explicitly routes mutation requests to update_shared_checklist.

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 openWorldHint=true, and the description goes further by naming the concrete consequence: removing an item also wipes its tick history. It also rules out a feared side effect with "Does not send messages to anyone," which is exactly the kind of context annotations cannot express. It omits whether a call is atomic across the multiple arrays or whether partial application is possible.

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 activation condition, then the operation list, then two short sentences on side effects. The middle sentence is a long enumeration, but every clause maps to a real parameter group, so little 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?

With 10 parameters, an output schema, and rich annotations, the description covers purpose, credential, and destructive consequences adequately. The remaining gap is whether the add/edit/remove/mark arrays can be combined in a single call or must be issued separately — a meaningful question for a 10-parameter mutation tool that the description leaves unanswered.

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% and every parameter carries its own example and constraints, so the schema does the heavy lifting. The description adds only that ticking/unticking works "by number" and that the link must be the private organizer one — useful framing but not new semantics for individual fields.

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 (a shared checklist page) and enumerates the exact operations: add items, edit text/section/assignee/due, remove, tick/untick by number, rename, change note, close/reopen. This is clearly distinguishable from create_shared_checklist and show_checklist_results, which the agent can rule out 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?

"Use this when the organizer wants to..." gives a clear activation condition and even identifies the acting role (organizer) plus the required credential (private organizer link). It stops short of explicitly naming siblings as alternatives for the read and create cases, so the routing is implied rather than spelled out.

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