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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description's 'verifica' is consistent with a read-only check. The description adds some behavioral context by enumerating what is verified (auth, plan, Codex, imagegen availability), but does not disclose response shape or failure/edge behavior.

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 sentence with no filler, front-loading the verb and main subjects. The cryptic '$imagegen' prefix looks like an unresolved template variable, which slightly detracts from polish, but overall the description is appropriately sized.

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 status tool this is mostly adequate: it names what is checked and the annotations cover the safety profile. However, with no output schema, it would benefit from hinting at what the response contains, and the $imagegen term plus sibling overlap with imagegen_status remain unresolved.

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 per rubric. The description need not explain parameter semantics, and the empty schema confirms no arguments 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 uses a specific verb 'Verifica' (verifies) and names its targets: ChatGPT authentication, plan, Codex, and $imagegen availability. The scope is clear, but it does not differentiate from the sibling imagegen_status, which likely also reports on imagegen availability.

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 guidance is given on when to use this tool versus imagegen_status, generate_image, or edit_image. With a closely related sibling like imagegen_status, the potential for mis-selection is real and unaddressed.

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 the operation is not read-only and not idempotent, so the safety profile is covered. The description adds value by disclosing the preservation semantics and the $imagegen dependency, but it doesn't disclose output file behavior, whether inputs get overwritten, or any other side effects of the edit.

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 sentence with no filler words, front-loading the verb and the core behavioral guarantee. It is lean and well-ordered, though it is arguably too terse for a 10-parameter 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?

For a mutating, closed-world tool with 10 parameters, no output schema, and only 30% schema description coverage, a one-sentence description is under-specified. It omits output handling, mask-based editing semantics, image count limits, and what happens to the files after editing.

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 only 30%, so 7 of 10 parameters (size, quality, background, output_format, include_inline, output_filename, output_directory) lack schema documentation. The description does not compensate: it mentions editing, preservation, and local images, but never explains the mask, output, or formatting 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 a specific verb and resource ('edits local images') and adds a distinctive behavioral clause: it preserves anything the prompt doesn't ask to change. This clearly differentiates it from the sibling generate_image, which creates new images rather than editing existing ones.

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 the usage context — modify existing local images while keeping unspecified content intact — but it never explicitly names alternatives or exclusion conditions. An agent must infer that generate_image is the right choice for new image creation; no when-to-use vs. when-not-to-use guidance is 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 signal a non-read-only, non-idempotent mutation, and the description adds that generation consumes Codex quota from the ChatGPT account, a useful resource/rate context. However, it does not disclose output file behavior, failure modes, or whether edits are reversible, so it only partially carries the behavioral burden.

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 or redundancy. It loses a point only because the '$imagegen' phrasing is cryptic and the sentence omits useful context that could be included without bloat.

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 8-parameter tool with no output schema, the description is far too thin: it omits return behavior, how the output file is produced, the significance of Codex quota, and any relation to the sibling tools. It is minimally usable but leaves major gaps.

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 50% schema description coverage, the schema leaves quality, background, output_format, and include_inline undocumented, and the description adds no parameter-level meaning beyond the word 'imagem'. It therefore fails to compensate for the coverage gap.

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 ('Gera uma imagem') and adds a distinctive implementation/quota detail ('com $imagegen e a cota do Codex'), so an agent can tell it is a generation action rather than a status check. It does not explicitly contrast with edit_image, so it falls short of full sibling differentiation.

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?

There is no guidance on when to choose generate_image over siblings like edit_image or when to first check codex_account_status. The quota mention hints at a prerequisite, but no explicit when/when-not instructions 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 mark the tool readOnlyHint=true, and the description matches by saying it 'Mostra' rather than mutates. It adds a specific behavioral reassurance that the optional probe does not generate an image, which is useful beyond the boolean parameter name. No contradictions.

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 before adding a caveat. Every phrase earns its place and there is no redundant restatement of the tool name.

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, one-parameter, read-only tool, the description covers the operation, the main returned categories (backend, limits, output), and the key probe caveat. It is slightly vague about the shape/format of the returned output, but this is a minor gap for a status 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 description coverage is 0%, so the description must carry the meaning of run_non_consuming_probe. It refers to an 'optional probe' that does not generate an image, but it doesn't explain what enabling the probe actually does or how true/false changes the status call, leaving the agent to infer the 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 uses a specific verb ('Mostra') and names the status resource ('backend, limites e saída'), making it clear this is a read-only status/health tool rather than an image-generation action. It further differentiates from generate_image/edit_image by stating the probe does not generate an image, though it does not explicitly distinguish from codex_account_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 conveys the tool's context as a status check and includes a useful exclusion ('o probe opcional não gera imagem'), so an agent should not use it for generation. However, it never names sibling tools or states when to choose it over codex_account_status, leaving routing mostly implicit.

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