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

Annotations already cover openWorldHint, idempotentHint=false and destructiveHint=false. The description adds genuinely useful behavior not in the annotations: subscription-backed auth, 'uses plan limits' (quota constraint), and the asynchronous contract returning a background job that must be polled via chatgpt_job.

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 short sentences, front-loaded with the action, then the quota caveat, then the async follow-up. Every sentence carries a distinct fact with no 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 an async tool with no output schema, the description supplies the critical missing piece: it returns a job, not an answer, and chatgpt_job is how to retrieve it. Minor gaps remain (whether the job handle is returned inline, whether conversation_id is echoed back), but the agent can call 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 coverage is 100%, so the schema already documents prompt, model, conversation_id, and reference_images including the 4-image cap. The description only gesture at the conversation parameter via 'continue its conversation', adding no format or constraint detail beyond the schema — baseline 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?

States a concrete verb and resource ('Ask the subscription-backed OpenAI assistant a question') and adds the continue-conversation mode. It does not explicitly distinguish itself from chatgpt_generate_image, even though reference_images makes that boundary relevant, so it falls short of a 5.

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?

Usage is implied by the two modes ('a question or continue its conversation') and the follow-up instruction to poll chatgpt_job. There is no explicit when-not guidance or named alternative for image generation versus text prompting, which an agent must 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?

Annotations already declare idempotent, non-destructive and open-world, so the description adds real value beyond them: that consumed usage is not refunded and that cancellation is asynchronous and must be confirmed by polling. It does not state whether cancellation succeeds for already-terminal jobs, which is the remaining behavioral 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?

Three short sentences, action first, then the cost caveat, then the required follow-up. Every sentence carries distinct information with no repetition.

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 one-parameter mutation with no output schema, this covers the essentials: what is canceled, the billing consequence, and the verification step. Only the origin and format of job_id is missing for an agent to act without opening the 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 0%, so the description carries the burden, but it never mentions job_id — neither its format (the schema pattern is the only clue) nor where the agent obtains it (presumably from chatgpt_ask/generate). With a single self-describing required parameter the gap is modest, but it is not compensated for.

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 ('Cancel a queued or running generation') and scopes it to two job states, which separates it from generate/ask siblings. It doesn't name chatgpt_job or chatgpt_status explicitly, so the sibling boundary is only implied by the 'poll the job' sentence.

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?

'Queued or running' implicitly excludes finished jobs and 'Poll the job to confirm terminal status' gives a follow-up path, so usage is inferable. However, no alternative tool is named and there is no explicit guidance on what to do if the job is already terminal.

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 generation uses ChatGPT subscription limits, returns a background job, and promises no image until completion. It does not cover failure modes, rate-limit specifics, or output retrieval beyond polling chatgpt_job.

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 front-loaded and appropriately sized. The final sentence about no promised image slightly overlaps with the polling instruction, but it reinforces an important async expectation.

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 an async image-generation tool with no output schema, it covers the essential workflow: generate/edit, prompt content, background job, and polling. It could be more complete by mentioning how to retrieve the resulting image or referencing chatgpt_read_image.

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 all parameters are already documented. The description adds useful prompt guidance about describing size, composition, transparency, and edits, but it does not explain model, conversation_id, or reference_images beyond what the schema provides.

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 and resource: generate or edit images. It distinguishes itself from text siblings by naming image generation and editing, and it points to the async workflow via chatgpt_job.

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 clearly establishes the tool for image generation/editing and tells the agent to poll chatgpt_job after invocation. It lacks explicit when-not guidance or a direct comparison to sibling tools like chatgpt_ask or chatgpt_read_image.

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 readOnlyHint annotation, the description adds useful behavioral details: completed small images are returned inline, and running jobs should be polled rather than resubmitted. These points clarify runtime behavior that the annotations alone do not convey. It still does not mention rate limits or authentication requirements, but the added context is meaningful.

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 compact sentences with zero redundancy. It front-loads the retrieval purpose and then adds operational constraints and return behavior in an efficient sequence.

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 no output schema, the description appropriately mentions returned fields and inline images. However, for a tool with three parameters at 0% schema description coverage, the missing explanation of wait_seconds and include_images leaves the definition incomplete for an agent to invoke it optimally.

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%, so the description must compensate but does not. It never mentions the job_id, wait_seconds, or include_images parameters directly, leaving wait_seconds and include_images completely unexplained. The inline image statement loosely touches include_images behavior but is not explicit parameter guidance.

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 that this tool retrieves a generation job along with its response text, conversation ID, and image paths. It distinguishes itself from a generic status tool by specifying the job-specific output. However, it does not explicitly contrast itself with the sibling chatgpt_status or chatgpt_ask 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 phrase 'Poll running jobs; do not resubmit the original request' gives a clear usage context for this tool. However, it does not name alternative tools or explain when to use chatgpt_status versus chatgpt_job, leaving some ambiguity for an agent deciding between siblings.

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 only declare openWorldHint and destructiveHint=false, so the description carries the real behavioral load: it discloses that the call returns a URL to open and adds a security constraint ('never ask for a password or token in chat'). It stops short of stating whether a login attempt expires, can be repeated, or is superseded by chatgpt_cancel.

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, front-loaded with the action and its trigger, followed by the return behavior and the credential-safety warning. No filler or repetition.

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 no output schema, the description correctly fills the gap by explaining the return value (a URL for the user to open) and the credential-handling constraint. It lacks only lifecycle context — what happens on repeat calls and how it relates to chatgpt_status/chatgpt_cancel.

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 takes zero parameters, so the baseline is 4 and there is nothing the description could add on parameter semantics. The schema is empty and fully consistent with a no-argument login trigger.

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 ('Begin ChatGPT browser sign-in') and names the concrete output ('Returns a URL'), which clearly separates it from siblings like chatgpt_status, chatgpt_cancel, and chatgpt_ask. An agent can identify the operation without opening the 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?

Gives an explicit trigger condition: 'when the user asks to connect their account.' However, it names no exclusions or alternatives — for example, it doesn't say to check chatgpt_status first, or that chatgpt_cancel aborts a pending login, leaving some inference to the agent.

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 openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: results are returned inline (not as a link), only bridge-produced images are readable, and there is a 4 MiB per-image ceiling — a constraint an agent cannot see anywhere else.

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, with the core action and the retrieval identifiers front-loaded and the constraints trailing. Nothing is repeated from the schema or annotations.

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 two-parameter read with no output schema, the description covers the essentials: what is returned (image content inline) and the two hard limits (bridge-origin, 4 MiB). It omits failure behavior for unknown or expired IDs, which is the only meaningful gap.

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%, so the description must carry parameter meaning and it does not. It names 'job and image IDs' but never explains where those IDs come from (presumably chatgpt_generate_image or chatgpt_job), that both are required, or what the identifier format is — even though the schema imposes a strict pattern.

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 ('Return a previously generated image inline') plus the identifiers used to address it. The word 'previously' implicitly separates it from the sibling chatgpt_generate_image, but the differentiation is left for the agent to infer rather than stated outright.

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 'Only reads images produced by this bridge' clause tells the agent the scope of valid inputs, which is useful. However, it never says when to call this versus chatgpt_generate_image or chatgpt_job, and gives no guidance on what to do if the image was not produced here.

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 openWorldHint=true, so the safety profile is covered. The description then adds the non-obvious behavioral guarantee that the call does not consume generation/quota ("without generating content"), which is exactly the extra context an agent needs before using it as a cheap pre-flight check.

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?

A single front-loaded sentence: verb first, then the list of coverage areas, then the differentiator. Nothing redundant.

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 no parameters and no output schema, the description carries the burden of describing what comes back, and it does so at the category level (login state, models, usage limits, bridge setup). A hint about the response shape or what a failure means would push this to a 5.

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 takes zero parameters, so the baseline is 4. The description correctly implies a call with no arguments and enumerates the status areas being probed, leaving no ambiguity about inputs.

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 ("Check") and enumerates the exact resources it reports on: subscription login, available text models, usage limits, bridge setup. The phrase "without generating content" separates it from the generation siblings (chatgpt_ask, chatgpt_generate_image) without needing the schemas.

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 clearly frames a diagnostic/read-only context ("without generating content"), which tells an agent this is the non-consuming probe to run before or instead of generation calls. It stops short of explicitly routing among siblings, e.g. not saying to use chatgpt_login when this reports a logged-out state.

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