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

With no annotations, the description carries the behavioral burden; it discloses headless-browser execution and markdown output, which is useful context. It omits operational details such as auth/rate limits, JavaScript/wait behavior, timeouts, and failure handling, leaving clear gaps.

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 front-loaded sentence with no filler. The provider names add useful context without unnecessary 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 a simple URL-fetch tool with full schema coverage, the description gives enough to invoke it correctly: the required url and markdown output are clear. It could be more complete about behavior without annotations, but the remaining gaps are modest.

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 url and the ignored actions parameter are already documented in the schema. The description adds no parameter-level meaning beyond the high-level operation, so the 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?

States a specific verb and resource: loads a URL in a headless browser and returns the page as markdown. It is clear what the tool does, but it does not explicitly distinguish itself from siblings such as read or search.

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 when-to-use or when-not-to-use guidance beyond the implied operation of loading a URL. It does not explain how this differs from read or search, nor when a headless-browser fetch is preferred.

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 and does disclose non-obvious traits: an authenticated web session is required, persistence differs by transport (stdio and local bridge write a file and return a path; direct hosted HTTP returns inline artifacts and never writes paths), and a session token enables follow-up edits. It omits side-effect details such as quota consumption on the underlying provider accounts, rate limits, or latency, which keeps it below a 5.

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?

Purpose is front-loaded in the first sentence, and the remaining sentences each map to a distinct mode/parameter decision. A few clauses restate schema descriptions almost verbatim, which is minor redundancy rather than 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 a five-parameter tool whose behavior changes with transport, the description covers the mode split, the persistence model, and the return shape (path vs. inline artifacts) even though no output schema exists. What remains unstated is failure behavior and the provider/failover mechanism, so it is strong but not 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?

Schema coverage is 100%, so the baseline is 3; the description goes further by explaining the interaction between parameters – `prompt` and `file` combine for an edit, `session` is the value returned by a prior call, and `path` only matters for the modes that persist locally. It does not explain `provider` selection or failover, which is left entirely to the schema text.

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 pair and resource ('Generate or edit an image') plus the channel ('via a logged-in web session'), so an agent knows exactly what the tool does. It also distinguishes its own sub-modes (new vs. edit vs. continue-session), and none of the siblings (browser, read, search, usage, deep_research) overlap with it.

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 explicit routing for each path: pass `prompt` for a new image, pass `file` in local stdio mode to edit, pass `session` to continue a ChatGPT image chat. It covers the conditions for using each parameter but never states a when-not-to-use case or what happens on failure, so it stops short of a 5.

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 and discloses the long runtime, the async polling pattern for chatgpt_web, the session lifecycle, and that model is ignored during chatgpt report polling. It adds substantial operational context beyond the schema.

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 front-loads purpose and timing, then explains session flow, then lists knobs. It is dense but every sentence carries operational detail; it could be more scannable with bullets, but it remains readable and appropriately sized for a complex 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 an 11-parameter tool with no annotations and no output schema, the description covers the critical multi-step session lifecycle, timing expectations, provider-specific behavior, and key knobs. It leaves return-format minutiae to runtime behavior but explains the essential async patterns an agent must 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 coverage is 100%, so the baseline is 3, but the description adds meaning about the session/query relationship, the cost and speed tradeoff of depth='deep', and how provider-specific extras are discovered via usage. It goes beyond the structured parameter definitions.

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: 'Deep research over multiple sources' and lists the providers it can use. It implicitly distinguishes from siblings like search through 'deep research' and 'may take minutes', but does not explicitly name an 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?

It explains the session workflow for gemini_web and chatgpt_web (pass the session with query 'start' or a revised request) and that chatgpt requires a follow-up call 5-30 minutes later. It does not explicitly say when to choose this over search or browser, or when not to use it, but the context is 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?

With no annotations at all, the description carries the full burden and does disclose the key non-obvious behavior: silent auto-escalation to a headless browser when the plain read returns empty, plus a provider override that bypasses the default priority order. It omits failure semantics, timeouts, auth requirements, and any cost/latency implications of the browser escalation.

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, front-loaded with the core action and output format before the edge cases. The pointer to usage(provider=…) replaces what would otherwise be a long enumeration of per-provider modes.

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 3-parameter read tool with no output schema and no annotations, the description covers output shape, escalation behavior, and provider selection adequately. The remaining gap is sibling disambiguation against 'browser', which matters because the description itself invokes headless browsing as an internal fallback.

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 and the schema already documents url, mode, and provider. The description reinforces mode as a 'provider-specific escape hatch' and points to usage(provider=…) for the exact value set, which is helpful but largely duplicates the schema's own explanation.

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 ('Read a URL') plus the output form ('return its main content as clean markdown'), which is far more informative than the bare name 'read'. It does not differentiate itself from the overlapping 'browser' sibling or from 'search', so the reader must infer those boundaries.

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 (read a known URL; escalate automatically when plain read is empty) and routes the agent to usage(provider=…) for provider extras. However, it never says when to pick this over the 'browser' tool or when 'search' is the better starting point, and no exclusions 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?

With no annotations at all, the description carries the full burden and does so: it discloses the two distinct return shapes, that web-provider results carry a `session` token for follow-up turns, that chatgpt_web performs a full chat turn with web search on by default, that hosted HTTP mode rejects `file` inputs due to filesystem access, and that providers are consulted in a priority order unless forced. These are non-obvious traits an agent could not infer from the schema.

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?

Front-loaded with the core purpose, then layered detail about result shapes, provider-specific behaviour, and where to look for the long tail. It is dense rather than verbose — every sentence carries information, though the parenthetical shorthand ('Niche knobs', 'structured extract…') is slightly cryptic on first read.

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?

Ten parameters, no annotations, and no output schema — the description compensates by explaining return shapes, session continuation, and the mode/model knobs it deliberately does not enumerate, delegating that to `usage`. Nothing an agent needs in order to call it correctly or interpret the response is left unstated.

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 still adds cross-parameter meaning the schema lacks — that a follow-up message goes in `query` when `session` is set, that `file` implicitly targets grok_web when no provider is forced, and that `topic` steers backend selection rather than just labelling a niche. It does repeat some schema text (recency, domains, max_results) without enrichment.

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?

Names a specific verb and resource ('Web search') plus the scope ('across quota-aware providers'), and splits the tool's behaviour into two concrete result classes: ranked title/url/snippet results from API providers versus synthesized answers with sources from web providers. An agent can tell what it will get back without opening the schema, and the description points to `usage` for anything outside this tool's core remit.

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 concrete conditional guidance: use `mode="chat"` on chatgpt_web to answer from the model alone, attach `file` only in local stdio mode, and call `usage(provider=…)` for provider-specific extras like scholar/patents/places. What is missing is routing against the siblings — nothing says when to prefer `deep_research` or `browser` over this tool, and there are no exclusion conditions.

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 supplied, the description carries the full disclosure burden and does well: it explains that locked modes (grok Expert/Heavy on a lapsed sub) read 0/0, which is genuine interpretation guidance for the output rather than a restatement of the name. It also distinguishes the richer logged-in-session payload (live per-tier limits, model/mode catalog, thinking levels) from the basic snapshot. It omits auth prerequisites and whether calling it has any cost.

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?

Purpose and default behavior are front-loaded in the first clause, and the optional-parameter expansion follows in a clearly conditional second sentence. The em-dash-heavy phrasing and jargon like 'escape-hatch `mode` values' cost a little readability but no sentence is 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 single-optional-parameter, read-oriented introspection tool with no annotations and no output schema, the description does the heavy lifting: it describes both return shapes and how to interpret a degenerate 0/0 result. Only ancillary facts an agent might want — auth state, whether quota numbers are cached or live — are absent.

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 already 100%, so the baseline would be 3, but the description goes further by unpacking what the `provider` value actually yields — niches, escape-hatch `mode` values, and ready-to-copy example calls — and by giving a concrete example (grok Expert/Heavy on a lapsed sub) that maps the enum to observable behavior.

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?

Names a specific verb and resource ('Show remaining free quota per account and provider for the current period') and then enumerates the exact contents of the response, including assigned proxies and per-tier limits. The scope is unambiguous and cannot be confused with any sibling tool (browser, read, search, create_image, deep_research).

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 tells the agent how to choose between the two invocation modes: pass `provider` for that backend's full capability sheet, omit it for the compact all-provider snapshot. What is missing is any guidance on when this tool is not appropriate or what to do if a provider isn't configured.

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