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. It usefully discloses the bidirectional behavior (done=false reopens), but says nothing about side effects (e.g. timestamps), idempotency, what happens if the task is already in the target state, or required permissions for a 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 tight sentence that front-loads the primary action and folds the inverse case into a parenthetical. No wasted words.

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-parameter toggle tool with no output schema, the description covers the essential behavior. It falls short only on edge-case behavior and permissions, which a mutation tool would ideally mention, but the core is sufficient.

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 schema already documents both id and done, including the 'false to reopen' semantics. The description's parenthetical essentially restates the schema's own done description, adding no new format or constraint detail. 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 ('Mark a task as done') and even covers the inverse operation ('reopen it with done=false'), so the agent knows both directions of the toggle. It does not differentiate itself from the sibling update_task, which an agent could plausibly reach for to change task state.

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 prefer this over update_task, nor any prerequisites or conditions. The only usage-adjacent signal is the parenthetical reopen case, which is about the parameter, not about tool selection.

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 burden. It implies a mutation, but says nothing about required permissions, whether titles must be unique, whether the label is global or scoped to a project/task, or what happens on duplicate input. For a write operation with zero annotation coverage this is a substantial 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 short sentence is structurally clean and front-loaded, but here brevity reflects under-specification rather than efficient communication. Nothing beyond the tool name is conveyed.

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 mutation tool with no annotations, no output schema, and only a third of parameters documented in the schema, the description should explain scope, permissions, and return behavior. It covers none of these, leaving the agent unable to call it confidently.

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 33% (hexColor is documented, title and description are not). The description adds no parameter meaning at all, so it fails to compensate for the undocumented title (required, non-empty) and description 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?

"Create a new label." is a near-verbatim restatement of the tool name (create_label) and title (Create label). It states a verb and resource but adds no scope, no distinguishing detail, and no differentiation from siblings such as list_labels or create_task. This is tautology rather than a genuinely informative 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?

There is no guidance on when to use this tool, what prerequisites apply (e.g. whether a project or task must exist first), or how it relates to siblings like list_labels. The agent is left to infer everything from the name.

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 for a mutation tool. It says nothing about required permissions, whether the parent project must exist or be accessible, what happens on duplicate titles, or what is returned after creation. Only the nesting behavior is disclosed.

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 waste, with the core action front-loaded and the optional behavior second. Nothing is padded or repeated.

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 three-parameter tool with complete schema coverage and no output schema, the description is minimally adequate. However, as a mutation with no annotations, it leaves auth requirements, parent-project validity conditions, and post-creation behavior 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%, so the schema already documents title, description, and parentProjectId. The description's mention of nesting adds only marginal framing over the schema's 'Parent project id for nesting', which is the baseline-3 case.

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 new Vikunja project'), which cleanly separates it from siblings like create_task and create_label that share the verb but target other resources. It does not explicitly name or contrast with a sibling doing the same thing, but the resource specificity is enough for an agent to disambiguate.

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 'Optionally nest it under a parent project' implies when the parentProjectId path applies, but there is no explicit when-to-use guidance, no prerequisites, and no stated alternatives or exclusions. Usage is left to inference from context.

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 for a write tool, and it says almost nothing: no permissions required, no note on whether the created task is returned or how its id is obtained, no side effects such as notifications or watchers, no error behavior for invalid projectId. The only behavioral hint is the lookup routing.

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, front-loaded with the action and followed by the lookup guidance. No filler. It is arguably too terse for an 8-parameter write tool, but nothing in it 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?

For a mutation tool with 8 parameters, no annotations, and no output schema, the description should at least indicate what happens on success and whether there are permission or validation constraints. With no output schema, the return value (e.g., the new task id) is undocumented anywhere in the definition.

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 titles, dates, priority scale, and label/project ids are all documented in the schema itself, making 3 the baseline. The description adds only the pointer that label ids come from list_labels, which is marginally useful but not compensating for anything missing.

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 task in a project'), which is unambiguous. It does not, however, differentiate itself from siblings like create_project or create_label beyond the resource name, which is enough here but not exceptional.

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 concrete prerequisite routing: use list_projects to find the projectId and list_labels for label ids. That is real when/how guidance an agent can act on. It does not state any when-not conditions or alternatives to create_task itself.

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. It does not disclose that this is a non-mutating read, what happens on a missing or unauthorized id (error vs. empty), or anything about permissions. For a mutation-free lookup the risk is low, but the disclosure gap remains.

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; the resource and keying parameter come first. It is efficient but arguably under-specified rather than truly concise, which keeps it off a 5.

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 no output schema and no annotations, the description gives the minimum needed to invoke it correctly. It could usefully note that it returns a single project object and how missing ids behave, but nothing essential 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 description coverage is 100% and the sole parameter is documented as 'Project id' in the schema, so the description correctly need not repeat it. It adds no format or range meaning beyond the schema, so 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 ('Get') and resource ('one Vikunja project by id'), which cleanly distinguishes it from list_projects and the task/label siblings. It stops short of 5 only because it adds no scoping detail (e.g., whether archived/deleted projects are returned).

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 explicit when-to-use guidance. An agent can infer it is the single-item counterpart to list_projects, but the description never says so, nor does it mention prerequisites or what to do if the id is unknown.

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. It implies a read operation and enumerates the returned fields (description, dates, priority, labels, assignees), which is valuable since there is no output schema. However, it omits any mention of permissions, error behavior, or whether the task must exist, so it is only partially transparent.

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 efficient sentence that front-loads the core purpose and then lists key return fields. Every word 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?

Given the absence of an output schema and annotations, the description usefully lists the primary returned fields. It could additionally state that the task must exist or describe error conditions, but for a simple get-by-id tool it is largely 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 single required parameter 'id' has full schema description coverage ('Task id'). The description adds no meaning beyond the schema—it does not explain ID format, source, or edge cases. With schema coverage at 100%, the baseline of 3 is correct.

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 uses a specific verb ('Get') and resource ('a single task'), and the word 'single' implicitly distinguishes it from list_tasks. It does not explicitly name the sibling it contrasts with, so a 4 is appropriate.

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 on when to use this tool versus list_tasks, get_project, or update_task. The description only states what it returns, leaving usage context entirely to inference.

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 burden, and it is thin. It hints at return content ('with ids') but says nothing about pagination behavior despite page/perPage parameters, nor about permissions, ordering, or result limits.

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; the verb and the practical reason for calling it appear immediately. Nothing redundant or padded.

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 read-only list tool with no output schema, the description covers the essential purpose and the key return field (ids). However, with three parameters at 33% schema coverage and no annotations, pagination and filtering behavior are left undisclosed, which an agent invoking it with search or paging would need.

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 33% (only 'search' is documented) and the description compensates for none of it. It never mentions page, perPage, or the search filter, so an agent must infer pagination and filtering entirely from bare schema properties.

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 ('List labels') and adds scope ('available to the user') plus the reason the output matters (ids for create_task / update_task). This separates it from the write-oriented sibling create_label, though it does not explicitly contrast with list_projects or list_tasks.

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 clause 'with ids for use in create_task / update_task' makes the calling context clear: fetch this before populating label ids on tasks. No explicit when-not-to-use or named alternative is given, so it stops 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?

No annotations are provided, so the description carries the burden. It discloses the return fields (id, title, description, identifier, parent) and implies a read-only, permission-scoped operation, but is silent on pagination behavior and on the fact that archived projects are excluded by default.

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 tight sentences, no filler, with the core purpose front-loaded ahead of the return-shape and follow-up-usage details.

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?

There is no output schema, but the description helpfully enumerates the returned fields, which covers the main gap. Still missing for a 4-param list tool are pagination semantics and the archived-exclusion default, and no annotations back-fill them.

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 50%: search and includeArchived are documented, while page and perPage are not, though their types and defaults make them conventional. The description adds no parameter meaning at all, so it neither compensates for nor worsens the coverage gap.

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 ('List Vikunja projects') with the scoping condition 'the user can access', which an agent can distinguish from the singular get_project. It does not explicitly name a sibling to contrast with, so it falls just short of full sibling differentiation.

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 line 'Use the id with list_tasks or create_task' gives a downstream hand-off hint, but there is no guidance on when to use this versus get_project or when listing is preferred over fetching a single project. Usage is implied rather than stated.

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 exist, so the description carries the full burden and does reasonably: it discloses the default open-only filter, the exact returned field set (and what is omitted), and the override semantics of `filter` over includeDone. It is silent on pagination behavior and rate limits, which leaves some 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?

Three information-dense sentences with no filler: scope first, then return shape and the get_task handoff, then the default behavior and both query shortcuts. Every clause carries actionable content.

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 9-parameter, zero-annotation, no-output-schema list tool, the description covers the essentials and even enumerates the return fields, which substitutes for a missing output schema. Pagination semantics across pages are the one omission.

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 56%, and the description fills much of the gap: it explains both boolean flags, and gives concrete Vikunja filter syntax examples (`done = false && due_date < now+7d`, `labels in 3, 5`) that go well beyond the schema's one-line field list. page, perPage, sortBy, orderBy and search are left to the schema, which documents them adequately.

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 with scope ('across all projects or within one project'), and explicitly carves out what it does not return, routing agents to the sibling get_task for descriptions. An agent can distinguish it from get_task and the mutation 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?

Gives concrete usage conditions: default open-only behavior, assignedToMe=true for the current user, and raw filter strings for advanced queries with worked examples. It names get_task as the alternative for full task detail, though it does not state when a caller should prefer search or when filters should be avoided.

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 and does disclose the highest-risk behaviors: partial-update semantics (unspecified fields are preserved) and the destructive replace semantics of labelIds. It does not cover permissions, reversibility, error behavior, or the response shape, but the mutation-critical traits are front-loaded and unambiguous.

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, zero filler, and the core semantic (only passed fields change) is placed first. Each remaining sentence addresses a distinct footgun: null clearing, label replacement, sibling routing.

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 11-parameter mutation tool with no annotations and no output schema, the description covers the behaviors most likely to cause a wrong call. What is missing is error/permission behavior and what the call returns, which matters more here than for a simple read tool.

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 45%, with done, title, and description carrying no inline docs at all. The description compensates meaningfully by explaining the null-clears-a-date convention and that labelIds replaces the whole label set, but it adds nothing about done/title/description semantics beyond their names.

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 (existing task) with the scope qualifier 'fields of an existing task', and explicitly distinguishes itself from the sibling complete_task. An agent can route between update_task and complete_task 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?

Gives explicit conditional guidance: only passed fields change, pass null to clear a date, labelIds replaces rather than appends, and directs to complete_task for the mark-done-only case. The alternative and the conditions that select it are named outright.

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