drafturl

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

With no annotations provided, the description carries the full burden. It discloses the external platform (DraftURL) and the shareable URL outcome, but omits behavioral details like storage permanence, rate limits, content validation rules, or error handling.

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 single-sentence description is appropriately sized at 12 words, front-loaded with the action verb, and contains no redundant 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?

Given the lack of output schema and annotations, the description partially compensates by mentioning the shareable URL return value. However, it does not specify the response structure format or document lifecycle details expected for a state-mutating 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?

With 100% schema description coverage, the schema adequately documents parameters. The description adds the platform context ('DraftURL') not present in the schema, but does not expand on parameter semantics like the optional nature of the title or password protection behavior.

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 ('Create') with clear resource ('HTML or Markdown document') and platform ('DraftURL'), effectively distinguishing it from siblings like delete_document and update_document.

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?

While the action is clear, the description provides no guidance on when to use this tool versus siblings (e.g., when to create new vs update existing) or prerequisites like authentication requirements.

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 full burden and successfully discloses two key behavioral traits: the soft-delete nature (data is not permanently destroyed) and the ownership authorization requirement. Could improve by mentioning idempotency or return value, but covers primary safety concerns.

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 totaling nine words. Perfectly front-loaded with the action ('Delete'), immediately qualifies the deletion type, and ends with the critical constraint. Zero redundancy or filler 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 single-parameter deletion operation without output schema, the description provides sufficient context by clarifying the soft-delete mechanics and ownership requirements that would typically appear in annotations. Adequately complete for the tool's complexity level, though mentioning the return value would strengthen it further.

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?

Input schema has 100% description coverage for the single 'slug' parameter ('Document slug identifier'). The description does not add parameter-specific semantics or usage examples, but with complete schema coverage and only one simple required parameter, the baseline score of 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 specific verb 'Delete' and resource 'document', clearly distinguishing from CRUD siblings (create_document, get_document, list_documents, update_document). The parenthetical '(soft delete)' adds critical behavioral specificity that differentiates this from a permanent hard delete.

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?

Provides clear prerequisite constraint 'Requires ownership' which establishes necessary permissions context. While it doesn't explicitly name sibling alternatives, the ownership requirement effectively signals when the tool cannot be used. Lacks explicit 'when-not-to-use' comparisons against update_document.

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. It successfully communicates the ownership requirement but omits other important behavioral details such as response format, what happens when the slug doesn't exist, or whether metadata includes timestamps/authors.

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 consists of two highly efficient sentences with zero redundancy. It is properly front-loaded with the core purpose ('Get a document...') followed by the constraint ('Requires ownership'), with every word serving a distinct informational purpose.

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 single-parameter retrieval tool without an output schema, the description adequately covers the essential operational contract: what is retrieved (content and metadata), how to identify it (slug), and the access constraint (ownership). Minor gaps remain regarding error conditions and return value structure.

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%, establishing a baseline score of 3. The description references the parameter ('by slug'), confirming its usage, but doesn't add supplementary semantic information like format constraints or validation rules beyond what's already in 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 clearly states the specific action ('Get'), resource ('document'), and retrieval method ('by slug'). It effectively distinguishes from siblings: unlike 'list_documents' which returns multiple items, this retrieves a specific single document by identifier, and unlike create/update/delete, this is clearly a read operation.

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 the critical prerequisite 'Requires ownership,' indicating authorization constraints. However, it lacks explicit guidance on when to use alternatives (e.g., 'use list_documents if you don't know the slug') or error handling when ownership requirements aren't met.

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?

Discloses pagination behavior and authentication requirement; acceptable given no annotations exist, though lacks details on rate limits or result structure.

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?

Extremely concise two-sentence structure with no redundancy; every word conveys essential functional or constraint 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?

Adequate for low complexity (2 optional params, no nesting); covers core functionality and constraints, though could mention return type given lack of output schema.

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?

Mentions 'pagination' conceptually aligning with page/size parameters, but schema has 100% coverage so baseline 3 is appropriate with no additional parameter detail needed.

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?

Clear verb-resource pair ('list documents') and operation type distinguishes from CRUD siblings, though doesn't explicitly clarify batch vs single-item retrieval.

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 authentication requirement and pagination pattern (implying bulk retrieval), but lacks explicit when-to-use guidance versus get_document.

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. It successfully discloses the ownership requirement and mutation nature. However, it omits behavioral details such as whether unspecified fields are preserved (partial update semantics), error handling for non-existent documents, or idempotency guarantees.

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 with zero waste. First sentence front-loads the action and scope; second sentence provides the critical ownership constraint. 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?

Adequate for a mutation tool with 100% schema coverage but no annotations or output schema. The ownership requirement is crucial context. However, gaps remain regarding error conditions, return value description, or explicit confirmation that omitted fields remain unchanged.

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%, providing detailed descriptions for all four parameters including format hints (HTML/Markdown, max 200 chars) and special behavior (empty string removes password). The description lists the updatable fields but adds no semantic information beyond what the schema already provides, meeting the baseline for high-coverage schemas.

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 specific verb 'Update', resource 'document', and enumerates exact updatable fields (content, title, password). The phrase 'existing document' effectively distinguishes this from the create_document sibling.

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?

Provides a critical constraint ('Requires ownership'), implying authorization requirements. However, it lacks explicit when-to-use guidance contrasting with siblings (e.g., does not clarify 'use this instead of create_document for existing docs') or mention of partial vs full update patterns.

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