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

Beyond annotations (readOnlyHint:false, openWorldHint:true), the description discloses the browser opening, loopback redirect, waiting behavior, and state outcomes (completed/pending). It also mentions the need for an OAuth client, adding valuable context beyond the structured 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?

Three sentences, no waste, and the core purpose is front-loaded. It includes necessary details (loopback, wait, states) without fluff, striking a good balance between completeness and brevity.

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 explains the state machine (completed/pending) and the waiting behavior. It covers the prerequisite and points to status and auth_status. It does not mention error conditions explicitly, but the overall flow is sufficiently clear for an agent to call the tool 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% with both parameters fully documented. The description adds no new parameter-level meaning; it merely reinforces the behavior of wait_seconds. Baseline 3 is appropriate since the schema already carries 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 clearly states 'Begin the OAuth sign-in' with a specific verb and resource, and distinguishes itself from siblings by referencing auth_status for the pending state and status for the client prerequisite. It leaves no ambiguity about the tool's role.

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 explicitly explains when to call auth_status (when state is pending) and notes the prerequisite of an OAuth client (see status). It does not contrast with all siblings, but the flow is clear and actionable.

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?

readOnlyHint already signals this is a safe read, and the description adds meaningful behavioral context: the optional blocking behavior, the state vocabulary, and the timeout behavior. It doesn't contradict the annotation.

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 first states the purpose and possible states, the second explains the optional blocking parameter. No filler or redundant restatement.

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 read-only poller with one optional parameter, the description is complete: it names the states, explains the blocking behavior, and ties the tool to the auth_start workflow. No output schema exists, but 'report the state' plus the enumerated states sufficiently conveys the return concept.

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 schema already fully documents wait_seconds, so the baseline is 3. The description adds value by explaining that wait_seconds blocks until the sign-in settles or time runs out, giving the parameter a behavioral meaning beyond 'seconds to wait.'

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 names a specific verb ('Report'), a clear resource ('the sign-in started by auth_start'), and enumerates the exact state values (idle/pending/completed/failed). This makes it easy to distinguish from auth_start (which starts the flow) and the unrelated sibling 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 tool's context is clear: it should be used after auth_start and can optionally block via wait_seconds. It doesn't explicitly spell out when not to use it or name alternatives, but the resource and workflow are specific enough to guide selection.

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 annotations, the description discloses important behavior: without confirm it only reports planned commands; with confirm it executes commands, may run `gcloud auth login`, and may open a browser if no account is active. It also reveals that a project may be created or generated, and that steps 3-4 are returned as next_steps—all useful side-effect context for an agent.

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 dense but well-structured: it front-loads the core purpose, then explains the two execution modes, then clearly summarizes what the tool cannot do. Every sentence contributes a distinct fact, and there is no filler or repetition of the 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?

With no output schema present, the description adequately covers the key returned artifacts: planned_commands, next_steps, and console_form with sample values. It also explains the side-effect behavior and the division between automated steps and manual steps, giving an agent enough information to call the tool correctly and interpret its output.

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 well. The description adds context around the overall execution flow, but it largely mirrors the parameter descriptions for confirm, project_id, and login_if_needed rather than adding meaning beyond them. Baseline 3 is appropriate because the schema carries the semantic weight.

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 names a specific verb and resource: prepare/configure a Google Cloud project and enable the Drive API for users with the gcloud CLI. It also distinguishes itself from the remaining setup steps by explicitly saying steps 3-4 cannot be automated and are returned as next_steps, making its scope clear against sibling 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 gives clear guidance: it is for users who have the gcloud CLI, and it fully explains the two modes—plan-only without confirm, and execution with confirm—so an agent knows when to ask for approval. It does not name sibling tools as alternatives, but it does state the boundary between what this tool can do and what must remain as next_steps.

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 only readOnlyHint=false in annotations, the description carries the behavioral burden and adds valuable context: it copies rather than moves, never exposes the secret in conversation, and copies nothing when the path is omitted. It does not mention overwrite behavior when the config file already exists, so it stops short of full transparency.

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, front-loaded with the primary action, then the conditional list mode and confirmation step. Every sentence earns its place with no redundant phrasing.

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 with no output schema, this is nearly complete: it covers both call modes, the list output ordering, and the required user-confirmation step. The only gap is unspecified behavior for invalid paths or existing config-file collisions.

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 schema already documents path with 100% coverage, so the baseline is 3. The description reinforces that omitting the path triggers listing, but it adds no new format or value constraints 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 states a specific verb and resource: copy a downloaded OAuth client JSON into drivelift's config directory. It also documents the optional list-only mode, making the tool's dual purpose unmistakable and distinct from siblings like upload or auth_start.

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 gives explicit invocation rules: call without a path to list candidates, and call with a path to import, including a confirm-then-call-again protocol. It does not explicitly contrast with sibling tools, but the two modes are so clearly specified that an agent knows exactly when to invoke it.

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 the description aligns by calling this a 'Report' operation. It adds meaningful context beyond annotations by listing the returned fields, the state enum, and the specific instruction to relay next_steps verbatim, as well as noting the BYO OAuth client and drive.file scope. No contradiction with annotations exists.

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 with the core purpose and then packs in output details, user-relaying instructions, console_form usage, and OAuth context. It is longer than average but every sentence carries actionable information; only the final contextual sentence is slightly extra, though still relevant.

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 carries the full burden of explaining return values, and it does so thoroughly: state enum, message, next_steps, urls, and console_form. It also tells the agent exactly how to relay next_steps and when to show console_form as a table, making this complete for a zero-parameter read-only 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?

The tool has zero parameters and the schema coverage is 100%, so there is nothing for the description to explain about inputs. The baseline of 4 applies here; the description appropriately focuses on outputs instead.

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 opens with a specific verb and resource: 'Report whether drivelift can upload to Google Drive right now.' It enumerates the exact return states (no_client / no_token / token_invalid / api_disabled / ready), which clearly distinguishes this setup-level status check from the sibling auth_status tool without needing to inspect 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?

The description implies when to use the tool — whenever you need to know if an upload is currently possible — and gives post-invocation guidance ('When not ready, relay next_steps to the user verbatim'). However, it never explicitly compares itself to alternatives like auth_status or states when not to use it, so selection guidance is left to inference.

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=false, destructiveHint=false, and openWorldHint=true. The description adds valuable behavioral context: conversion rules for various file types, default destination, and error behavior with next_steps. It does not contradict the annotations and provides meaningful detail beyond them, though it could mention potential side effects like overwriting existing files (though it doesn't, which is fine as it's not destructive).

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 yet comprehensive, with each sentence adding distinct value. It is front-loaded with the core action and return value, then logically progresses to conversion behavior, destination, and error handling. No wasted words; every sentence earns its place.

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 tool with 4 parameters, all documented, and no output schema, the description is complete. It explains return value (URL), conversion behavior, folder handling, and error handling. The complexity is moderate, but the description covers all necessary aspects for an agent to invoke it correctly, including edge cases like folder_id visibility.

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 have descriptions. The description significantly enhances this by explaining the convert enum in detail (what happens with auto, which file types map to which Google format), cautioning about folder_id with drive.file scope (404 risk), and clarifying the name default (extension dropped when converting). This goes well beyond the schema's terse descriptions.

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 (upload a local file), the target (Google Drive), and the outcome (return its URL). It also details conversion behavior for different file types, which distinguishes it from any potential sibling upload tools. The verb 'upload' is specific and the resource is unambiguous.

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 clear context on default behavior (My Drive root) and when to use folder_id, and it explains error handling when drivelift is not set up. While it doesn't explicitly state when not to use this tool or name alternatives, the sibling tools are all auth/setup related, so the usage context is clear. It could be more explicit about prerequisites (e.g., auth required), but the mention of drivelift setup covers that.

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