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

Annotations already mark this as read-only, and the description adds useful behavioral boundaries: it uses the official auth status, makes no inference call, and does not return remaining Claude allowance. It does not describe permissions or failure modes, but the added caveats are 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?

Three tight sentences front-load the core purpose, then immediately add the most important behavioral limits. There is no redundant or filler content.

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 no-parameter, no-output-schema status tool, the description explains the Claude return value and rules out remaining allowance. However, it does not fully clarify what the tool returns for Codex authentication even though Codex is named in the primary check.

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 there is no parameter semantics to explain. The baseline score for a parameterless tool is appropriate, and the description does not need to invent 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 gives a specific verb and resource: check local Codex and Claude subscription authentication. It also distinguishes itself from inference/task operations by stating 'No inference call', helping an agent separate it from the sibling task 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 makes clear this is for authentication/status checking rather than task submission or inference. It also sets two exclusions, no inference call and no remaining Claude allowance, though it does not explicitly name which sibling to use for other operations.

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?

The readOnlyHint annotation already covers the safety profile, and the description adds genuinely non-obvious interpretation context: that cache/input token fields are separate provider fields and that a list-price estimate is not an actual subscription charge. These caveats prevent misreading of returned usage data, though nothing is said about behavior for unknown or expired task ids.

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?

Four short sentences with no filler; the core purpose is front-loaded and each following sentence adds a distinct caveat. Phrasing is slightly telegraphic but every sentence carries information.

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 does some of the work by characterizing the return (status, answer, usage) and warning about field semantics. It still omits the terminal-state list, how to obtain a valid task_id, and error behavior, which matter for a polling 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?

There is one parameter, task_id, with 0% schema description coverage, and the description says nothing about its expected format or provenance. The parameter is self-evident by name, but the description does not compensate for the missing schema documentation.

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 ('Retrieve') and resource ('a Claude task') plus exactly what is returned: status, final answer and usage. The 'Claude' qualifier implicitly separates it from the sibling get_codex_task, though the description never names that sibling explicitly.

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 line 'Queued/running is not completion' implies this should be polled until terminal state, which is useful implied usage. However, there is no explicit guidance on when to call this versus get_codex_task or bridge_status, and no note on where the task_id comes from (presumably submit_claude_task).

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, so the description usefully spends its words on return contents and the non-obvious caveat that queued/running must not be treated as completed. That is genuine behavioral context beyond the annotations, though nothing is said about retention or error responses.

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 with the core action and return payload up front, followed by the critical interpretation caveat. No wasted text.

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-parameter read tool with no output schema, the description enumerates what comes back and warns about in-progress states, which is most of what an agent needs. The task_id provenance is the one remaining 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 coverage is 0% and the single task_id parameter is undocumented in the schema. The phrase 'previously submitted task' weakly links task_id to the submit tools, but the description does not state the ID's origin or format.

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?

Specific verb 'Retrieve' plus the concrete resources returned (status, final answer, token usage) for a 'previously submitted task'. The Codex scope is only conveyed by the tool name, not the description text, so the split from get_claude_task is implicit rather than stated.

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?

'For a previously submitted task' implies the polling/precondition context and the warning about queued/running states steers result interpretation. However it never says when to choose this over get_claude_task or how often to poll.

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?

Goes well beyond the annotations (which only say it is not read-only, not idempotent, not destructive): no shell/local-file/MCP/messaging/publishing capability, subscription auth checked before every task, model pinned to Sonnet, single shared active task, 20-minute timeout, no API fallback, and a warning not to infer allowance from token counts. This is exactly the operational context an agent needs before invoking.

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?

Dense and front-loaded, with the capability boundary and constraints stated early and no filler. The telegraphic sentence fragments ('No shell, local-file, MCP, messaging or publishing tools.') cost a little readability but each clause carries distinct information.

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?

No output schema exists, and the description covers the operational essentials: async execution, timeout, polling, auth, one-task concurrency, and the no-fallback limitation. It does not say what the submission returns (e.g., a task identifier to use with get_claude_task), which is the one remaining 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 carries the burden and does explain both parameters: task is a text-analysis payload (with the test string as an example) and allow_web enables optional public web research. It omits the task 1–50,000 character limits and the allow_web=false default, which remain schema-only.

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 ('Delegate') and resource ('a user-authorized text-analysis task') plus the execution channel ('official Claude Code subscription login', 'Uses Sonnet'). The Claude/Codex split is self-evident against sibling submit_codex_task, so an agent can pick the right submit tool without opening either 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 concrete usage conditions: allow_web=true for public web research, polling required after submission, one shared active task at a time, and a prescribed first test ('Reply exactly CLAUDE_BRIDGE_TEST_OK'). It stops short of explicitly naming get_claude_task as the polling companion, leaving that 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?

Rich disclosure beyond the annotations: it consumes a specific account's allowance, runs asynchronously, disables inherited user config, transfers no credentials or full memory, and requires the Windows host to remain awake. The 'read-only mode' phrase describes the delegated run rather than the tool itself, so it does not squarely contradict readOnlyHint=false, but the ambiguity is worth noting.

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?

Dense but efficient: the core action and its constraints are front-loaded, and each subsequent sentence adds a distinct operational fact (cost, async, isolation, host requirement, exclusions). 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 submission tool with no output schema, the description should say what comes back and how to retrieve the result; it never mentions get_codex_task or any task identifier. It covers the important preconditions well, but the post-call workflow is left to inference from sibling names.

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 single 'task' parameter has 0% schema description coverage, so the description must compensate; it does partially by advising 'supply only relevant task context' and giving a concrete example task string (BRIDGE_TEST_OK). It says nothing about the 50,000-character limit, expected formatting, or how self-contained the task text must be.

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 (delegate/submit) and resource (a task to the locally signed-in Codex account) plus the exact model, gpt-6.1-sol. It also carves out scope against siblings by excluding Claude and Google access, so an agent can separate it from submit_claude_task.

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 clear usage context: one task per call, only relevant context should be supplied, the host must stay awake, and it explicitly excludes bulk scraping and Claude/Google access. It does not, however, explicitly route to siblings such as get_codex_task for retrieval or submit_claude_task for Claude work.

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