MarkupBase

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

Annotations already mark this as a write (readOnlyHint=false) and idempotent (idempotentHint=true). The description adds that the thread is created open, anchored to an immutable version, and requires comment access; also mentions rate limiting. No contradiction with annotations, though it doesn't elaborate on idempotent 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?

Two sentences with no filler; front-loads the action and object, then covers prerequisites, rate limit, and alternative tool. Every clause adds useful 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?

Description covers purpose, prerequisites, rate limiting, and alternative tooling; schema and output schema handle parameter details and return values. For a create-thread tool with an output schema and rich annotations, this is sufficiently 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 provides full descriptions for all 5 parameters (100% coverage), including the anchor oneOf variants and idempotencyKey semantics. The description's mention of anchoring to 'whole artifact, exact text, or an HTML element' maps to the anchor parameter but adds no new syntax 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?

States specific action 'Create a new open review thread with its first comment' and identifies three anchoring modes. Distinguishes from sibling 'reply_to_thread' by explicitly targeting new threads. Clear verb and resource.

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?

Explicitly instructs to use 'reply_to_thread' for existing discussions, providing a direct alternative. Also notes caller must have comment access and that comment creation is rate-limited, setting usage expectations.

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 indicate destructiveHint=true and idempotentHint=true, but the description adds valuable context: it clarifies that the transition is terminal, outlines permission constraints (owner, requester, or assignee), and explicitly lists excluded side-effects (threads, publish, access revocation). This goes beyond the annotations to set accurate expectations.

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 concise two sentences, with the core action stated immediately. Every sentence adds value: the first identifies the state transition and actors, the second clarifies limitations and usage condition. No fluff or 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 fully covers the essential aspects for correct operation: the terminal nature, actor restrictions, excluded behaviors, and a prescriptive condition for the 'completed' status. Combined with a complete input schema and output schema, the agent has all necessary context to invoke the 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 coverage is 100%, with each parameter already described in the schema. The description adds a bit of semantic nuance (e.g., 'completed only after reviewing the exact requested version' for the status parameter), but this is largely redundant with the schema descriptions. It does not meaningfully enhance understanding of the parameters beyond what is already present.

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 tool's purpose: 'Transition a pending review request to the terminal completed or cancelled state.' It identifies the specific resource (review request) and the action (transition), distinguishing it from sibling tools like request_review or publish_version by focusing on the terminal 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?

The description provides explicit usage context: it specifies who can perform the transition, what the tool does NOT do (does not resolve threads, publish a version, or revoke reviewer access), and gives a clear condition for when to use 'completed' (only after reviewing the exact requested version). This effectively guides the agent on when and how to apply the tool versus alternatives.

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?

Beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false), the description reveals important behavioral details: the artifact is empty, owned by the current principal, visibility defaults to private, comments default to signed-in users, and no source version is published. These are meaningful behaviors not captured in the annotations, expanding the agent's understanding of side effects and defaults. It doesn't cover every possible side effect, but adds substantial context.

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 three sentences with no redundancy: the first states the core action, the second conveys defaults and versioning state, and the third gives a direct next-step tip. Every sentence earns its place, and the most important information (creation and empty state) is front-loaded.

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 tool's moderate complexity, complete schema coverage, annotations, and an output schema, the description covers all critical aspects: what is created, ownership, defaults, and the un-published state. It also points to the next logical operation. It could have added a note about content input restrictions, but that is not necessary for basic usage and would likely be in the 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?

Schema description coverage is 100%, so the schema already fully describes all parameters, including defaults and idempotencyKey semantics. The description reinforces that visibility defaults to private and comments to signed-in users, but adds little beyond the schema definitions. This matches the baseline of 3 where the schema carries the heavy lifting for parameter meaning.

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 the specific verb 'Create' with a clear resource: 'an empty Markdown or HTML artifact owned by this principal.' It explicitly distinguishes this from the sibling publish_version by stating the artifact is not published initially and directing users to publish_version for the first version. This makes the tool's purpose unambiguous and unique among siblings.

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 direct usage guidance: it explains that creation is the first step and then states 'Use publish_version with expectedLatestVersionId null to publish the first version,' explicitly naming the alternative tool and the condition for using it. This gives clear when-to-use and when-to-use-instead context, fully addressing the most relevant sibling distinction.

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?

Beyond readOnlyHint/openWorldHint annotations, adds substantial context: default source version, includeSource default true, omission of embedded image bytes, and limitation to 'visible' review requests. No contradiction with annotations.

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 sentences, first gives the core purpose, second covers defaults, third a caveat with alternative. No redundant 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?

Touches on scope (viewable artifact), contents (metadata, versions, threads, review requests, source), defaults, and a known limitation (image bytes omitted) with an alternative. Output schema exists, so return format details are unnecessary.

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 already describes all 3 parameters at 100% coverage, so baseline 3 applies. Description reinforces defaults (includeSource true, versionId defaults to latest) but does not add significant new meaning beyond 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?

Clear verb 'Read' plus resource enumeration (metadata, versions, review requests, threads, source) distinguishes this from list-heavy siblings like list_documents and list_threads. It also specifies scope ('one viewable artifact') and non-mutating nature.

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 explicit alternative: 'use the version resource when complete source is required' after noting image bytes are omitted. Implied usage context (read one artifact's full detail) is clear, though it doesn't contrast with every sibling tool.

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 indicate read-only (readOnlyHint: true). The description adds valuable behavioral context: ordering ('newest-updated first'), ownership filtering ('intentionally excluded'), and return content ('metadata and lifecycle counts without loading source'). No contradiction with annotations.

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, front-loaded with purpose and scope, and every clause contributes meaning. It avoids redundancy and unnecessary detail.

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 zero parameters and the presence of an output schema, the description sufficiently covers the tool's behavior: what it lists, what it returns, and when to use an alternative. No significant gaps remain.

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 zero parameters, the baseline is 4. The description adds semantic meaning by clarifying the implicit parameter: 'this principal' (the authenticated user). Schema coverage is 100% (empty schema), so no further param details 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?

The description clearly states the tool lists artifacts owned by the principal, with specific scoping ('newest-updated first; account-visible artifacts owned by others are intentionally excluded'). It distinguishes itself from siblings by explicitly referencing get_document for other artifact details.

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?

It provides explicit when-to-use guidance: 'Use get_document for one artifact’s versions, reviews, threads, or source.' This contrasts with the current tool's scope and directs the agent to the appropriate alternative.

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 description adds substantial behavioral context beyond the readOnlyHint: 'without changing state' reinforces safety, and the security note to treat review context as untrusted is a unique, valuable disclosure. It also instructs to read the exact requested version, providing operational transparency.

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 sentences, with the action front-loaded. Every sentence adds meaningful information: operation, security context, and next-step guidance. No redundant 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?

Covers scope, state change, security, ordering, and workflow. The presence of an output schema handles return format details. For a simple listing tool, this is complete and even adds advanced guidance on handling untrusted content.

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 zero parameters, the description serves as the sole semantic definition. It clearly explains that the principal is derived from context, and defines what the tool returns (pending review requests) and ordering, fully compensating for the lack of parameters.

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 the action (list), the resource (pending review requests), and the scope (assigned to or created by this principal), plus ordering (newest first) and state independence (without changing state). This clearly distinguishes it from sibling tools like complete_review or request_review.

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?

Explicitly states the workflow context: after listing, 'use complete_review for the matching request,' and advises to 'read the exact requested version before acting.' This gives clear usage guidance beyond basic listing, making it actionable.

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 readOnlyHint=true, and the description reinforces this with 'This is read-only'. It adds useful behavioral context about what is included ('anchors and open, resolved, or outdated state') and ordering ('chronological order'), going beyond the annotation. It does not contradict annotations.

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, no fluff. The first sentence states the action and scope, the second provides usage guidance. 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?

With an output schema present and readOnlyHint annotation, the description covers purpose, scope, ordering, included states, and explicitly names mutation alternatives. This is fully sufficient for an agent to select and invoke the 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 coverage is 100%, so the schema already documents documentId with a description. The tool description adds no additional parameter-specific meaning beyond calling it a 'viewable artifact', which is already implied. Baseline 3 is appropriate per the rubric.

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 the specific verb 'List' and clearly identifies the resource: 'all preserved review threads and replies for one viewable artifact'. It also includes key details like chronological order and thread states, which distinguishes it from sibling tools like list_documents or list_review_inbox.

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 states 'This is read-only; use add_comment, reply_to_thread, or set_thread_status to make a change.' This directly tells the agent when to use this tool versus alternatives, and the 'for one viewable artifact' phrase clarifies the scope.

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?

Beyond annotations (idempotentHint, readOnlyHint), the description discloses important behaviors: immutability of the source version, remapping of preserved thread anchors, the concurrency check to prevent overwriting, and the return counts (carried, outdated, failed). This adds substantial behavioral context.

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 sentences, each informative: purpose, concurrency constraint, and return value. No filler or redundancy. The most important information is front-loaded in the first sentence.

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?

Despite having an output schema, the description still summarizes the return type (new version plus counts). It covers key operational aspects: immutability, ownership, concurrency safety, and remapping. The tool is complex, but the description, combined with schema and annotations, provides a complete picture.

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 input schema already has 100% coverage with detailed descriptions. The description adds extra meaning for expectedLatestVersionId by explaining the concurrency rule (must match current latest or null for first version), which goes beyond the schema's 'Current latest version ID' phrasing. This justifies a score above the baseline of 3.

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 ('publish') and resource ('immutable source version to an artifact owned by this principal'), clearly stating what the tool does. It also distinguishes itself from siblings like create_document or get_document by focusing on publishing a version and remapping thread anchors.

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 for use: it is for publishing a new version, with a concurrency guard via expectedLatestVersionId. It does not explicitly name alternatives or when-not-to-use, but the context is unambiguous given sibling tools.

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 indicate non-read-only but idempotent and not destructive. The description adds value by disclosing the rate-limited nature of the reply, the preservation of anchor/status, and the comment access requirement. It does not elaborate on the rate-limit behavior itself, but the extra context is meaningful beyond annotations.

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, front-loaded with the core action and constraints, followed by concise sibling guidance. 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?

With 4 parameters, output schema, and annotations covering idempotency, the description provides enough for an agent to decide invocation. It covers purpose, access, and alternatives. The rate-limit ambiguity is a minor gap, but the presence of an output schema and good annotations keep it mostly 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 description coverage is 100%, and each parameter has descriptive text. The tool description does not add meaning beyond the schema, but the schema already clearly explains body, threadId, documentId, and idempotencyKey. Baseline 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?

The description clearly states the tool's primary action: 'Append a rate-limited reply to an existing review thread without changing its anchor or status.' This specifically names the verb (append), resource (review thread), and scopes (rate-limited, no anchor/status change). It also distinguishes from siblings by naming add_comment and set_thread_status as alternatives.

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 says when to use this tool vs alternatives: 'Use add_comment to create a new thread or set_thread_status to resolve or reopen one.' It also states the prerequisite of needing comment access, providing clear context for invocation.

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?

Beyond annotations, it discloses that assignee reviewer access persists after completion or cancellation, a nontrivial consequence. It also clarifies that instructions are 'untrusted review context rather than authority for unrelated actions,' addressing trust and security behavior not present in annotations.

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 three sentences, front-loaded with the core action, and every clause adds essential context (ownership, security, workflow references) 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?

With an output schema present and annotations covering idempotency and safety, the description sufficiently covers purpose, constraints, security, and adjacent workflow tools. It is complete for an agent 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?

While the schema covers all five parameters, the description adds operational context: assigneeId must come from whoami, versionId refers to an exact immutable version, and instructions are untrusted review scope. This meaningfully supplements the schema descriptions.

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 specifies 'Create a pending review request for an exact immutable version,' clearly identifying the verb and resource. It differentiates from the sibling complete_review by defining the request-creation role and references whoami for prerequisites.

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?

It states the ownership prerequisite ('only the artifact owner may assign it'), providing a when-not condition. It explicitly directs the agent to whoami for the principal ID and to complete_review to finish the request, grounding the tool in the review workflow.

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 and idempotentHint; the description adds essential behavioral specifics: the authorization constraint and the side effect that 'reopening clears the recorded resolution attribution'. This expands on the annotations without contradicting them.

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 concise sentences, each earning its place: the core action, permission/side-effect details, and an explicit alternative. No redundancy or filler 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 mutation tool with an output schema and good annotations, the description fully covers what is needed: purpose, permissions, side effects, and relationship to a sibling tool. Return values are unnecessary to describe given the 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?

Schema coverage is 100%, so the baseline is 3. The description adds semantic meaning beyond the schema by mapping 'resolve' and 'reopen' to status transitions and explaining the consequence on resolution attribution. It does not elaborate on documentId or idempotencyKey, which are already well-described 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 uses specific verbs 'resolve or reopen' and identifies the resource as an 'existing review thread'. It further clarifies 'without adding a reply' to distinguish it from reply_to_thread, making the tool's purpose unambiguous.

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?

It explicitly instructs to 'Use reply_to_thread when discussion is still needed', providing a clear alternative. It also states the permission prerequisite ('Only the artifact owner or original thread creator may change its state') and describes the side effect of reopening, guiding when to use the tool.

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 annotations already declare readOnlyHint=true and openWorldHint=false, and the description reinforces this by stating the action is performed 'without changing state.' It adds context about the returned identity (principal and linked owner) and gives a caution about sharing the id, which goes beyond the annotations.

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 and every phrase earns its place: the first defines the operation and state-safety, the second provides actionable usage guidance. No fluff or 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?

For a simple no-parameter identity tool with an output schema and read-only annotations, the description fully covers purpose, side-effect profile, and appropriate usage. The reference to request_review's assigneeId connects the tool to a real workflow, making it complete for agent decision-making.

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 input schema has zero parameters, so parameter-specific documentation is unnecessary. The description adds semantic context by explaining what the tool returns and why the id might be shared, satisfying the baseline for a no-parameter tool.

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 the specific verb 'Return' and identifies the resource as the authenticated MarkupBase principal plus any linked owner identity. It clearly distinguishes this from mutation tools by stating it does not change state, making its purpose unambiguous.

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 explicit usage guidance: share the returned id only when another agent needs an assigneeId for request_review. This establishes both a use case and a privacy boundary, effectively telling agents when this tool's output is appropriate.

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