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

Beyond annotations (readOnlyHint=false, destructiveHint=false), the description discloses important behaviors: the secret payload is NOT echoed back, a token is sent if PWPUSH_API_TOKEN is set, some instances allow anonymous push creation, and v1 instances treat 'qr' as text. These details add value beyond the structured annotation fields and help set 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 efficiently structured: purpose first, then key behavioral notes, then file vs. text/url/qr usage. Every sentence carries distinct information, and the length is appropriate for the tool's complexity. No 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?

Given 10 parameters and no output schema, the description adequately covers critical context: return URL, non-echo behavior, auth token/anonymous option, file push mechanics, and legacy v1 quirk. It is complete enough for an agent to correctly select and invoke the 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 coverage is 100%, so the baseline is 3. The description adds meaning by explaining parameter interactions: file_paths forces a 'file' kind, payload is optional when file_paths are given, and 'qr' behaves differently on v1. This goes beyond individual parameter descriptions and clarifies the overall use.

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 opens with a clear verb+resource: 'Create a Password Pusher secret link and return its sharing URL.' It explicitly states the tool's primary function and distinguishes it from siblings like expire_push and list_active_pushes by focusing on creation. The purpose is unmistakable.

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 context on when to use the tool: share the returned html_url with the recipient, use file_paths for file pushes, set payload and kind for text/url/qr pushes. It also notes token/anonymous modes. Lacks an explicit 'use this instead of X' alternative comparison, but the guidance is contextually strong.

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 destructiveHint annotation, the description adds critical details: 'IRREVERSIBLE' and 'destroys the payload and any attached files for good'. It also mentions the auth requirement, providing meaningful context for a destructive operation.

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 brief and impactful, with each sentence providing essential information: the action, irreversibility, and required credentials. It is well-structured with the warning 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?

For a simple destructive tool with one parameter and no output schema, the description covers all necessary aspects: what it does, irreversible consequences, and authentication requirements. No additional information is needed 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?

The schema already provides 100% coverage for the single parameter url_token with a clear description. The tool description does not add additional meaning about the parameter, so the baseline score of 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?

The description clearly states the verb 'expire' and resource 'push', and explicitly says 'delete' and 'IRREVERSIBLE'. It distinguishes itself from siblings by being the destructive action, while other tools like create_push and preview_push are non-destructive.

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 usage for permanently deleting a push and notes the required authentication (PWPUSH_API_TOKEN). It does not explicitly name alternatives or state when not to use, but the sibling context makes the purpose clear.

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 destructiveHint=false, so the safety profile is known. The description adds valuable context beyond annotations: it specifies that auth is required and discloses the contents of the audit log (views, IPs, user agents). This enriches the agent's understanding of side effects and prerequisites.

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 sentence that front-loads the main purpose and immediately adds the auth requirement. Every word earns its place, with no filler or repetition. It is appropriately sized for a simple read tool.

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 simplicity (2 params, 1 required, no output schema), the description covers the core return value and the key context. It could mention pagination or the fact that page defaults to 1, but the schema already provides those details. The description is sufficient to understand what the tool does and returns.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with both 'page' and 'url_token' already having descriptions. The tool description adds no extra parameter-level meaning beyond 'for a push', so the baseline of 3 applies; the schema carries the parameter semantics.

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 action ('Return') and the resource ('the audit log (views, IPs, user agents) for a push'), which unambiguously distinguishes it from sibling tools like list_active_pushes or expire_push. The specific content of the audit log adds precision.

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 usage by stating 'for a push', but it does not explicitly contrast with alternatives or state when to choose this tool over siblings. There is no exclusion or alternative naming, so it's clear in context but lacks direct guidance.

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 destructiveHint=false. The description adds the behavioral detail that no authentication is required, which is valuable beyond the annotations. It also clarifies the specific return content (version and feature flags).

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 sentence, front-loaded with the action and resource, and includes the key caveat about no authentication. Every word earns its place with no 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 zero-parameter, read-only tool with no output schema, the description sufficiently explains the return value and access requirements. The low complexity means no additional context is needed to invoke this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. The description does not need to explain parameters, and the empty input schema is fully covered. No additional parameter semantics are required.

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 returns the target instance's version and enabled feature flags. This is a specific verb-resource pairing that distinguishes it from the sibling push-management tools.

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 mentions 'no auth', implying it is safe for quick checks without credentials, but does not explicitly state when to use it versus alternatives. The context is clear enough for a simple read-only version retrieval, but no exclusions or alternative tool references are given.

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 destructiveHint=false, covering the safety profile. The description adds scope ('authenticated account's') and the active filter, but does not disclose additional behavioral traits such as pagination behavior or return format. This is similar to the get_calls calibration where a 3 was appropriate.

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 sentence, immediately front-loaded with the action and resource, with no superfluous words. It is concise while still delivering purpose and scope.

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 low complexity (one optional parameter, no output schema, strong annotations), the description is complete. It clearly states what the tool does, the scope, and the filtering criteria, which is sufficient for an agent to select and invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with the only parameter 'page' fully described in the schema. The description adds no additional parameter semantics, so the baseline of 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?

The description uses a specific verb 'List' with a clear resource 'pushes' and scope 'authenticated account's active (not yet expired)'. It directly contrasts with the sibling tool 'list_expired_pushes' by emphasizing 'not yet expired', fully distinguishing itself.

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 when to use the tool (for active pushes) and hints at the alternative via 'not yet expired', but it does not explicitly state exclusions or name alternative tools. Usage context is implied rather than directly 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds a useful scope ('authenticated account's') but does not disclose other behaviors like pagination details or return format. Given the annotations, the incremental value is moderate, aligning with a baseline acceptable disclosure.

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, concise sentence that states exactly what the tool does without any redundancy or filler. It is efficiently front-loaded and earns every word.

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 one optional parameter, the description plus annotations and schema provide sufficient information. The absence of an output schema leaves a minor ambiguity about return format, but the verb 'List' implies an array of pushes, so the overall completeness is strong.

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% for the single 'page' parameter, including a description 'Page number (50 per page)'. The tool description adds no additional semantic information about the parameter, so the schema carries the full burden—baseline 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 uses a specific verb 'List' with a clear resource 'expired pushes' and scope 'authenticated account's', making its purpose unmistakable and differentiating it from siblings like 'list_active_pushes' and 'get_push_audit'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives a clear context: use this tool when needing expired pushes of the authenticated account. However, it does not explicitly mention alternatives or exclusions, but the context is sufficiently clear that an agent can infer the appropriate use.

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 destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations by specifying 'WITHOUT consuming a view', which is a non-obvious behavior not present in the structured fields. However, it doesn't disclose potential rate limits or authorization nuances, which prevents a higher score.

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, tightly written sentence that front-loads the action ('Return') and result ('shareable secret URL') while adding a crucial caveat. Every word adds value, with no redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with one parameter and strong annotations. The description effectively communicates the core function and the distinctive 'without consuming a view' behavior. Although there is no output schema, the description hints at the return content (a URL), which is adequate for this tool's complexity.

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% for the single parameter (url_token), so the schema fully documents the parameter. The description adds no extra meaning about the parameter beyond saying 'a push', which is already implied by the schema. Baseline 3 is appropriate since the schema carries the burden.

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 returns a shareable secret URL for a push, using a specific verb ('Return') and resource ('push'). It also distinguishes itself from sibling tools like list_active_pushes or expire_push by adding the phrase 'WITHOUT consuming a view', which is a unique preview capability.

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 usage context—previewing a push without consuming a view—but does not explicitly mention when to use this tool over alternatives or exclude other scenarios. It lacks explicit 'when/when-not' guidance that would make it clearer, though some context is provided by the preview intent.

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