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

No annotations are provided, so the description carries full burden of behavioral disclosure. It conveys a state-changing operation ('mark done') but does not mention idempotency, reversibility, permissions, side effects, or response/error behavior. This is a significant gap for a mutation 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?

A single, front-loaded sentence with zero filler. It states the action, the object, and the parameter source without 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?

The description captures the core invocation details for a simple one-parameter tool, but it omits any indication of return values or error handling. For a state-changing tool with no output schema, the agent is left to guess what happens after the 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?

With schema description coverage at 0%, the description compensates by explaining that the 'resource' parameter is a resource path returned by list_tasks. This gives the agent actionable information beyond the schema's plain 'string' type, though it could specify the path format more precisely.

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 ('Mark a reminder done') and a specific resource ('reminder by its resource path'). It also disambiguates from sibling tools by referencing the prerequisite list_tasks, making its role distinct from create_task or delete_event.

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 'as returned by list_tasks' provides clear context: a caller must first retrieve the resource path from list_tasks before using this tool. While it does not mention exclusions or alternative tools, the prerequisite is explicit and sufficient.

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?

With no annotations, the description carries the full burden of behavioral disclosure. It reveals a meaningful behavioral trait: the write is read back and rolled back if altered by the server, so success means the stored card matches what was sent. This goes well beyond a generic 'create' description, though it doesn't cover auth, failure modes, or return value.

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 a clear front-loaded purpose and a valuable behavioral guarantee. Every sentence adds information; no redundancy or bloat.

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 is adequate for a simple create operation and gives a meaningful integrity guarantee, but it omits usage routing, parameter semantics, return shape, and error/rollback details beyond the core guarantee. Since there is no output schema or annotations, these gaps leave the agent partially to inference.

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 should compensate for the six parameters. It adds only entity-level context ('connect contact') and doesn't explain any field, especially ambiguous ones like 'addressbook' or 'organisation.' The parameter names are somewhat self-explanatory but that is schema value, not description value.

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: 'Add a contact.' This clearly distinguishes the tool from siblings like create_event, create_task, and search_contacts without requiring the agent to inspect 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 no guidance on when to use this tool versus alternatives such as search_contacts or list_collections. There is no mention of prerequisites, when not to use it, or how it relates to other contact-related tools. Usage is only implied by the action word 'Add.'

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?

With no annotations, the description carries the behavioral burden. It explicitly signals a mutating operation ('Add') and discloses an important behavior: the start format selects between timed and all-day events. It does not mention interaction with the all_day schema default or return behavior, but the core side effect is clear.

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 two sentences with no filler. The operation is front-loaded, followed immediately by the most important input formatting rule.

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 seven parameters, no annotations, and no output schema, this description is incomplete. It enables a basic call but leaves ambiguity around required title handling, end behavior, all_day interaction, timezone/calendar selection, and what the tool returns.

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 compensate, but it only clarifies the start parameter's format. The other six parameters—title, end, note, all_day, calendar, and timezone—receive no semantic guidance, leaving the agent to infer their meaning from names alone.

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: 'Add a calendar event.' This distinguishes it from sibling tools like create_contact and create_task, and from list_events/delete_event, because it explicitly names the target domain object.

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 intended use is implied clearly by 'Add a calendar event,' but the description provides no explicit guidance about when not to use it or which sibling tool to choose instead. There are no exclusion rules or alternative routing hints.

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?

No annotations are provided, so the description must disclose behavioral details. 'Add a reminder' implies a mutating creation operation, but it does not explain whether reminders are triggered, whether duplicates can occur, what permissions are needed, or what the response contains.

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 short sentence with no unnecessary filler. It is front-loaded with the core action, and every word is efficient, though the content is minimal.

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 five parameters, low schema coverage, no output schema, and no annotations, the description is far from complete. It omits key behavioral and parameter context that an agent would need to call the tool correctly and interpret 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 description coverage is only 20%, and the description adds almost no parameter meaning. It only restates that a due date is optional, which is already visible in the schema. title, note, calendar, and timezone remain unexplained.

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 verb and resource: 'Add a reminder', which suggests creating a task, but it uses 'reminder' rather than 'task', creating ambiguity. It does not clearly distinguish from create_event or other sibling tools beyond the object type.

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 about when to use this tool versus alternatives such as create_event or complete_task. The phrase 'optionally with a due date' hints at usage, but no exclusions or conditions 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?

No annotations are provided, so the description carries the full behavioral burden. While 'Delete' conveys destructiveness, the description does not disclose whether deletion is permanent, whether it affects related resources, what permissions are required, or what response/errors to expect. These are important gaps for a mutation tool without annotation safety signals.

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, front-loaded sentence with no filler. It conveys the action, target, and key parameter provenance efficiently, making it easy for an agent to parse quickly.

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 tool is simple, with one required parameter and no output schema or annotations. The description adequately explains the input and its origin, but it omits return behavior, error cases, and permanence of deletion. For a minimal tool this is acceptable, yet not fully 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 coverage is 0%, so the description must compensate for the undocumented 'resource' parameter. It does so meaningfully by explaining that the parameter is a resource path obtained from list_events, clarifying both the value's nature and its source. It stops short of providing format examples, but for a single parameter this is strong compensation.

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 action ('Delete a calendar event'), the target resource, and the required identifier ('resource path'). It clearly differentiates from sibling tools like list_events, create_event, and complete_task by indicating this is the deletion operation for calendar events.

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 provides clear context by noting the resource path comes from list_events, implicitly directing the agent to call list_events first. It does not explicitly mention when not to use the tool or name alternatives, but for a unique delete operation among the given siblings, this level of guidance is sufficient.

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?

With no annotations, the description carries the full behavioral burden. It implies a read-only listing and defines scope, but it does not describe the return shape, empty-result behavior, or any auth considerations. The 'exact name' hint adds some value, but the behavioral context stays thin.

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: the first states the action and resource, the second gives the practical use case. It is front-loaded and contains 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 zero-parameter list tool, the description provides the essential selection and invocation context. A minor gap is the lack of an explicit return format, but 'exact name' strongly implies the useful output field.

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 has zero parameters and the schema coverage is trivially 100%, so the baseline of 4 applies. The note about needing exact names adds practical context for how results may be used, even though there are no parameters to document.

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 ('List') and specific resources ('address books and calendars'), and clarifies the scope ('this account can reach'). This clearly distinguishes it from the contact, event, and task sibling tools without ambiguity.

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 explicitly gives a concrete situation for use: when the account has multiple collections and the agent needs the exact name. It does not name exclusions, but the alternatives are different resource types, so confusion is unlikely.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. 'Upcoming calendar events' only implies a read-only listing operation; it does not reveal sorting, date range behavior, pagination, or what happens when no events exist. The description does not contradict annotations because none exist, but it adds little behavioral depth.

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 three-word description is extremely concise and front-loaded, but it is under-sized for a tool with four parameters and no other documentation. While every word earns its place, the description sacrifices substance for brevity, making it less than 'appropriately sized.'

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 4-parameter tool with no annotations and no output schema, a single noun phrase is insufficient. The description lacks any information about event fields, ordering, timezone handling, or the meaning of the days parameter, leaving an agent to infer most important details from the schema and tool name.

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 start and timezone documented in the schema. The description mentions no parameters and does not compensate for the undocumented days and calendar fields. However, the schema already handles half the parameters, making this a borderline case; the description adds no value 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 description 'Upcoming calendar events' clearly identifies the resource (calendar events) and the scope (upcoming), which distinguishes it from sibling tools like list_tasks and list_collections. However, it is a noun phrase rather than an explicit verb+resource statement, and it does not explicitly differentiate from search_contacts or list_collections, so it falls 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 provides no guidance on when to use this tool versus alternatives such as list_tasks or search_contacts. There is no mention of context, exclusions, or conditions that would help an agent choose this tool over its siblings.

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?

With no annotations provided, the description carries the full behavioral burden, but it only says where tasks are stored. It does not disclose what the tool returns, whether completed tasks are included, ordering, read-only nature, or any other runtime 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 short and concise, but it is under-specified rather than usefully concise. It does not state the action or behavior the tool performs, so the single sentence does not earn 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 data-model context (VTODO on the calendar) is useful, but it is far from complete. There is no output schema, no annotation, no param semantics, and no differentiation from sibling tools, leaving an agent with critical gaps for invoking this tool 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 0%, and the description provides no parameter semantics. 'calendar', 'timezone', and 'include_done' are left entirely unexplained, so an agent cannot determine valid values or side effects.

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 'Reminders and tasks stored as VTODO on the calendar' describes a data model, not an action. It does not explicitly say the tool lists tasks, so an agent must infer the verb from the tool name. It adds some resource context but is closer to a tautology than a clear purpose statement.

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?

No guidance is given about when to use this tool versus alternatives such as list_events or create_task. The mention of VTODO and calendar suggests a relationship to calendar data, but there are no explicit usage conditions or 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?

No annotations are provided, so the description bears the full burden of behavioral disclosure. It adds the accent-insensitive behavior and the fields searched, which is useful. However, it does not explicitly state that the operation is read-only, nor does it clarify how limit/addressbook constrain the search or what the response looks like.

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 concise sentence, front-loaded with the verb and resource, then the search criteria and a behavioral nuance. No redundant words and easy to scan.

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 search tool the description is mostly sufficient, but it leaves gaps: it does not clarify whether addressbook filters to a single book or searches all books, what the limit applies to, or what the return data includes (there is no output schema). With no annotations, these gaps make it only minimally 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?

The schema documents query as a name fragment or phone digits, and the description expands this to name, organisation, note, email, and phone digits, plus accent-insensitivity. This adds meaningful detail beyond the schema for the main parameter. The limit and addressbook parameters are not enriched beyond their schema descriptions, so it is not fully complete.

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 (search) and resource (address book), and enumerates the searchable fields: name, organisation, note, email, or phone digits. This clearly distinguishes it from sibling tools like list_collections (listing) and create_contact (writing), so an agent can tell it apart.

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 provides a clear context for when to search contacts, but it gives no explicit when/when-not guidance and does not mention alternatives such as list_collections for browsing collections. The intended use is implied by the verb and resource, not stated directly.

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