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

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It indicates a state-changing operation ('complete') but gives no details on prerequisites beyond timing, potential side effects, error conditions, or what the function returns. For an OAuth completion step, an agent might need to know whether it can be called multiple times, what happens if called before authorization, or how to handle failures. This is a significant 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?

The description is a single, front-loaded sentence with zero wasted words. It places the essential condition ('after authorization in the browser') right at the start. Every word contributes to the meaning.

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 0-parameter tool with no output schema, the description covers the essential usage timing but omits other operational context. It does not explain the return value (which could be critical for the agent to know whether the connection succeeded), nor does it note any prerequisites beyond the browser step. The lack of an output schema raises the burden on the description to describe the result, which it fails to do. Still, given the simplicity, it is minimally adequate.

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, so the schema is trivially 100% covered. Per the calibration guidance, a 0-parameter tool gets a baseline of 4. The description does not add parameter-specific details (there are none), and that is acceptable because there is nothing 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 clearly states the tool completes the LinkedIn OAuth flow after browser authorization. The verb 'complete' and the specific context 'after authorization in the browser' make the purpose unambiguous and distinguishable from sibling tools like start_linkedin_connection, which initiates the flow. It is specific enough for an agent to understand the tool's role, though it does not explicitly name the alternative.

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 usage condition: 'after authorization in the browser' – implying this tool should be called only after the user has completed the browser-based OAuth step. However, it does not explicitly state when NOT to use it or mention alternative tools like start_linkedin_connection. The guidance is implied rather than explicit, so it meets the 'clear context, no exclusions' level.

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. The phrase 'without exposing credentials' is a useful behavioral disclosure about output sanitization. However, it does not mention side effects, preconditions, or what the tool actually returns.

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 compact sentence with the main action front-loaded and a valuable security qualifier appended. There is no filler 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?

Adequate for a zero-parameter status check, but because there is no output schema and no annotations, an agent is left guessing about the return shape and whether any connection must exist before calling it. A little more context would make it 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?

The tool has zero parameters, so the schema coverage is trivially complete. There is nothing for the description to add about parameter meaning, and the baseline for zero-parameter tools 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?

The description is precise: it names a specific verb ('Check'), a resource ('LinkedIn publishing configuration'), and adds a meaningful safety qualifier. It clearly distinguishes this from sibling tools that start/complete connections or prepare/publish posts.

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 explicit when-to-use or when-not-to-use guidance is provided. The tool name and sibling list imply this is for inspecting connection/publishing state rather than mutating it, but the description does not state this directly.

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 provides one valuable safety guarantee: the tool never publishes. However, it does not explain what 'prepare' actually does—whether it creates a draft, stores content, or simply returns a representation—so the behavior remains underspecified.

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 filler, and the most important behavioral fact ('This never publishes') is front-loaded in the second sentence. 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?

For a simple three-parameter tool, the description is nearly sufficient: the required text parameter is inferable, and the safety boundary is clear. Still, with no output schema and no parameter-level guidance, an agent does not know what the tool returns or what side effects, if any, 'prepare' has.

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 adds no meaning to text, altText, or imagePath beyond their names and schema constraints. The phrase 'for human review' hints that text is the reviewed content, but the description does not compensate for the absent parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb ('prepare'), a resource ('LinkedIn post'), and a clear goal ('for human review'). The explicit statement 'This never publishes' separates it from the sibling publish_linkedin_post without any 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?

'For human review' gives clear context for when to use the tool, and 'This never publishes' rules out the main alternative action. It does not explicitly name publish_linkedin_post or spell out 'use this when you want a draft instead of publishing,' but the intended usage is strongly implied.

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 disclosure burden. It usefully discloses the human-approval gate and the reviewed-status precondition, which are important behavioral traits. However, it does not mention that publishing is a public, likely irreversible action, nor any authentication or connection requirements.

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 efficient sentence with no filler. The key action and the critical safety condition are front-loaded, making it easy for an agent to grasp the tool's purpose 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?

For a publishing tool with no annotations, no output schema, and 0% schema description coverage, the description is too thin. It omits parameter details, return behavior, error conditions, and workflow integration with prepare_linkedin_post, leaving an agent with only partial guidance for correct invocation.

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 does not explain any parameter beyond implying that approval is required. Parameter names like text, altText, imagePath, and approved are somewhat self-explanatory, but the description adds no semantic detail to compensate for the absence of 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 uses a specific verb ('Publish'), a clear resource ('already-reviewed LinkedIn post'), and a defining condition ('only after explicit human approval'). This clearly distinguishes it from sibling tools like prepare_linkedin_post, which would handle drafting/review rather than final publication.

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 conveys the key usage condition: this tool should only be used after a post has been reviewed and explicitly approved by a human. It does not explicitly name prepare_linkedin_post as the prerequisite alternative, but 'already-reviewed' strongly implies the correct workflow position.

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 transparency burden. It states the action and return value clearly, but it does not disclose whether invoking this tool creates persistent state, whether the authorization URL expires, or whether user interaction is required to complete the flow.

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 communicates both the action and the expected result efficiently, containing only information needed for the agent.

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 tool with no output schema, the description sufficiently covers what the agent needs to know to invoke it: it initiates OAuth and returns the authorization URL. Minor context about the broader OAuth flow and how this relates to complete_linkedin_connection could add value but is not essential.

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, so the input schema is complete and there is nothing for the description to add. The description correctly focuses on the tool's action and output rather than inventing unnecessary parameter details.

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 ('Start') with a clear resource ('LinkedIn OAuth') and states the concrete output ('return the authorization URL'). This clearly identifies the tool's role and differentiates it from siblings like complete_linkedin_connection and linkedin_connection_status.

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 implies this is the first step in the LinkedIn OAuth flow, which is useful context alongside the sibling tool complete_linkedin_connection. However, it does not explicitly state when to use this tool versus alternatives, nor does it mention prerequisites or exclusions.

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