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

No annotations are provided, so the description carries full burden. It explains the action (cancel a pending submission) but does not disclose side effects, permissions needed, or post-cancellation state. This is adequate but lacks depth.

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 filler. Every word is necessary and front-loaded with the core verb and resource. Very efficient.

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 tool with two optional parameters and no output schema, the description covers the core purpose but omits prerequisites (e.g., item must be pending), return value, or what happens after cancellation. Adequate but not thorough.

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 descriptions for both parameters. The tool description adds no extra 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?

The description clearly states the verb 'Cancel' and the resource 'pending submission on Chrome Web Store'. It specifies the tool targets items in review, distinguishing it from sibling tools like publish, upload, or get.

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 context for when to use the tool ('to cancel an item currently in review'), but does not explicitly state when not to use it or mention alternatives. However, the context is clear enough against 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?

No annotations are provided, so the description carries the full burden. It discloses important constraints (incremental percentage, user count requirement) but omits behavioral details such as success/failure responses or whether the change triggers a publish. The description is moderately transparent but lacks depth.

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, no filler. It is front-loaded with the core action and follows with necessary constraints. Every sentence adds value.

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 has 3 parameters with full schema coverage, no output schema, and no annotations. The description covers the core action and constraints but lacks information about return values, error conditions, or post-effect behavior. For a simple mutation tool, it is adequate but not 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 the description repeats the constraint from the schema ('Must be larger than the current target percentage'). It adds the default behavior for itemId and publisherId, but overall does not significantly enhance understanding beyond the schema with 3 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 clearly states the action: 'Set the published deploy percentage for staged rollout on Chrome Web Store.' It uses a specific verb ('Set') and identifies the resource ('deploy percentage'), differentiating it from siblings like 'cancel' or 'publish'.

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 conditions: the new percentage must be higher than the current target, and the tool is only available for items with 10,000+ seven-day active users. However, it does not explicitly mention when not to use this tool or suggest 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?

With no annotations, the description does carry real weight: it discloses a v2 behavioral regression (no listing metadata) and that `projection` is unsupported. It says nothing about auth requirements, what the response actually contains, or whether missing IDs are required, which are material gaps for an otherwise read-shaped call.

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 with the identity/alias claim front-loaded and the alternative named second. No filler, though the version-2 constraint is repeated once across both sentences.

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 the deprecation story and the sibling alternative, which is the main complexity here. But with no annotations, no output schema, and zero required parameters, an agent still lacks guidance on whether `itemId` must be supplied and what the returned status looks like.

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 all three parameters, including the deprecation note on `projection`. The description only reinforces the `projection` removal and adds no detail on `itemId` or `publisherId` semantics, so it does not exceed the baseline.

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 ("Fetch publication status through v2") and immediately clarifies that it is an alias of the sibling `status`, which disambiguates a very generic tool name. It also distinguishes itself from `get-metadata-ui` by saying listing metadata is no longer returned here.

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 routes the agent away from this tool for draft listing text ("use get-metadata-ui") and tells it that `status` is an equivalent alias. It stops short of stating when/why an agent would prefer this over `status`, but the alias note makes that moot.

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 burden: it correctly signals a read of draft state and implies a signed-in browser session (reinforced by the headless first-sign-in parameter). It does not state what happens when not signed in, whether a browser is launched, or what is returned for unset fields.

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 tight sentences: the scope of the read first, then the draft-vs-published caveat front-loaded before any schema detail. Nothing is wasted and nothing essential is deferred.

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 read tool with no annotations and no output schema, the description covers what is read and from where, but leaves the return shape, empty-field behavior, and sign-in failure mode unexplained. Those gaps matter for a browser-driven tool whose headless/accountIndex params imply session dependencies.

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 itemId, headless and accountIndex are already fully documented. The description adds no meaning about how those parameters affect the read, which is acceptable at baseline 3 when the schema does the work.

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 (Read) and an enumerated resource (draft listing description, category, homepage, support URL) from a named source (the signed-in Developer Dashboard). The clause 'This is not the published listing' distinguishes it from the published-listing sibling, so an agent can select it without opening a 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?

The draft-vs-published distinction gives a clear context for use: call this to inspect the unpublished draft rather than live listing data. It stops short of naming the sibling to use for the published listing (likely 'get') or of stating prerequisites such as being signed in, so it is clear but not exhaustive.

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 must carry the full behavioral burden. It does not explain whether publishing is irreversible, what review or approval flow occurs, what permissions are required, how warnings are handled, or what happens on failure.

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 short clauses, front-loaded with the core action and resource. It is efficient, though it could optionally add one clarifying sentence about the publish workflow without becoming verbose.

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?

This is a no-annotation mutation tool with no output schema and six optional parameters, yet the description does not cover authorization, defaults from environment variables, review behavior, or the result of publishing. The schema covers parameter details, but behavioral context is substantially missing.

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 all six parameters. The description adds only a high-level mapping to publishType, deployPercentage, and skipReview, while omitting itemId, publisherId, and blockOnWarnings context.

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 a specific verb and resource: 'Publish an extension to Chrome Web Store.' It also names publish modes, but it does not explicitly distinguish this tool from siblings such as upload, deploy-percentage, or cancel.

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 lists supported modes ('immediate publish, staged publish, initial deploy percentage, and skip-review') but gives no guidance on when to choose publish versus upload, deploy-percentage, or cancel. There are no explicit exclusions or preconditions.

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 full burden. It correctly implies a read operation by using 'Fetch', but lacks details on safety, idempotency, authentication, or rate limits. The returned fields are listed, which is helpful but not comprehensive behaviorally.

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: one sentence stating purpose and a list of return fields. It is front-loaded with the action. Minor improvement could be structuring the return fields more clearly, but overall efficient.

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 no output schema, the description lists six key return fields, which is sufficient for an agent to anticipate the response. The tool has simple optional params; the description covers what the agent needs to know.

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% because both parameters have descriptions mentioning environment variable defaults. The tool description adds no additional parameter info, so it meets the baseline but doesn't enhance meaning 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?

The description uses the specific verb 'Fetch' and the resource 'extension on Chrome Web Store', clearly indicating the tool's purpose. It distinguishes itself from siblings like 'deploy-percentage' (specific deploy info) and 'get' (generic) by listing the comprehensive set of returned data.

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 when an overall status is needed, but no explicit guidance on when to use alternatives like 'deploy-percentage' or 'get'. No 'when not to use' or comparisons, leaving the agent to infer.

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, so the description carries the full burden and does well: it discloses that changes are saved as a draft (non-destructive, reversible, no review trigger), that a signed-in session is required, and that a reload is needed to confirm. It omits failure semantics and, critically, what happens when called with zero arguments given all 12 parameters are optional — whether it is a partial merge or a full overwrite.

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, both front-loaded: the first gives the supported scope and the verification step, the second gives the exclusions. No redundant restatement of the name or filler.

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 12-parameter, nested-object, no-annotation, no-output-schema tool, the description covers mutability, auth channel, verification, and exclusions. Remaining gaps are the return/response shape (no output schema exists, so a sentence on what is echoed back would help) and the semantics of the optional-only parameter set.

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 baseline is 3; the schema already marks unsupported fields and documents 'empty string clears it'. The description consolidates the supported/unsupported split, which helps, but adds no syntax, format, or interaction detail (e.g. category label matching, accountIndex choice) beyond what the schema states.

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 (save draft) plus the exact resource fields (listing description, category, homepage/support URL) and the channel (Developer Dashboard), which is far more precise than the name alone. It distinguishes itself from publish by stating 'Does not submit for review', but never names the closely-named sibling update-metadata-ui, so an agent has to infer the browser-driven vs. UI difference.

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?

'Does not submit for review' plus the explicit unsupported list (title/summary, raw payloads, icon uploads) gives clear when-not guidance with the redirect (change manifest and upload a new ZIP). It lacks an explicit 'use publish for X / use update-metadata-ui for Y' routing statement, but the boundaries are implied clearly enough to act on.

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 load and does well: it discloses that the write happens through a browser session against the live dashboard, that a reload is used to verify, and that review submission is out of scope. It does not mention auth prerequisites (beyond 'signed-in'), duration, or whether the update is partial vs. overwriting.

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, zero padding: supported fields first, verification behavior second, exclusions last. Nothing repeats the name or title.

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 12-parameter, nested-object mutation tool with no annotations and no output schema, the description covers scope, mechanism, and unsupported inputs adequately. It leaves unstated what a successful call returns and whether omitted fields are preserved or cleared, which matters for a save operation.

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 explains every field including the 'Unsupported:' notes. The description's list of unsupported inputs (title/summary, raw payloads, icon uploads) largely duplicates that, adding only the framing that they require a new ZIP or direct dashboard action.

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 concrete verb and resource set ('Save draft listing description, category, homepage or support URL') plus the mechanism (signed-in Developer Dashboard), and immediately separates itself from `publish` by saying it does not submit for 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?

The 'Does not submit for review' clause gives an explicit exclusion and implicitly routes the agent to `publish` for submission, but it never tells the agent when to prefer this UI-driven tool over the sibling `update-metadata`.

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 fully bears the burden of behavioral disclosure. It only states 'update an existing draft' but omits details such as authentication requirements, rate limits, effect on previous draft, or return value.

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 concise sentences: the action is front-loaded, and the note adds essential context without excess.

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 covers purpose and a key limitation, but lacks details on expected behavior (e.g., output, size limits, overwrite semantics) given the absence of an 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% (all parameters described). The description adds no additional meaning beyond the schema, meeting 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 clearly states 'Upload a ZIP file to update an existing Chrome Web Store item draft', using a specific verb and resource. It distinguishes from siblings like 'get' or 'publish' by specifying the action is for draft updates.

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 includes a note explicitly stating that creating new items is not supported via API and directs to the Developer Dashboard, providing a clear when-not-to-use. However, it does not contrast with sibling tools like 'update-metadata'.

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