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

The description goes beyond the annotations by disclosing important behavioral traits: it requires permission to read browser credentials, may trigger a macOS Keychain prompt, and explicitly states it 'Never returns cookies' — a critical clarification given the tool name. This adds value beyond the sparse annotations and sets clear expectations.

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 three sentences, each with a distinct purpose: state the action, list prerequisites, and disclose behavioral outcomes (keychain prompt, no cookies). It is front-loaded with the core purpose and avoids filler. Every sentence adds necessary 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?

For a zero-parameter tool with an output schema, the description covers all necessary context: prerequisites, permission requirements, potential system prompts, and what the tool does NOT return. The existence of an output schema handles return value details. The description is complete for an agent to invoke 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?

There are zero parameters, so the baseline is 4. The description adds no parameter-specific details because none are needed. It does provide context about the operation's inputs (Chrome, Figma session) which is relevant but not parameter semantics. Since the schema is empty, no further clarification is 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 clearly states the tool's function: 'Read Figma sessions from Chrome for setup or recovery.' It identifies the specific verb (read) and resource (Figma sessions from Chrome), and the context (setup or recovery) distinguishes it from siblings like setup_status (checking status) and setup_save_pat (saving a token). No ambiguity.

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 context ('for setup or recovery') and specifies prerequisites (permission to read browser credentials, user logged into Figma). It does not explicitly mention when not to use it or compare with alternatives, but given the sibling tools, the use case is clear. Slightly more explicit exclusion would make it 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?

Annotations indicate readOnlyHint=false and destructiveHint=false, which are consistent with the description's 'save' action. The description adds behavioral context beyond annotations: it validates the PAT, saves it, and rejects mismatched accounts. This provides useful operational details that an agent needs to know.

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 sentences with no filler. It front-loads the core action, then provides an important security-relevant alternative and a rejection condition. Every sentence adds value, making it efficient and well-structured.

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 tool with an output schema present, the description covers the essential purpose, usage guidance, and a behavioral constraint. It doesn't explain the output format (covered by the output schema) or prerequisites like having a saved browser account, but those are either implicit or handled elsewhere. Overall, it is complete enough for an agent to call 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?

The schema covers 100% of the parameter 'pat' with a clear description ('Figma Personal Access Token'). The description adds minimal extra meaning—only that it is 'already supplied by the user,' which is more about usage context than parameter semantics. Since schema coverage is high, the baseline of 3 is appropriate.

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 tool's action: 'Validate and save a PAT already supplied by the user.' It specifies the resource (PAT) and includes a rejection condition ('Rejects a PAT belonging to a different saved browser account'), making the purpose unambiguous and distinct from sibling tools like setup_status or setup_select_account.

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 advises an alternative method: 'Prefer local figmanage login --pat-only to keep tokens out of chat.' This gives a clear when-not-to-use instruction. However, it does not explicitly contrast with the sibling tools (setup_status, setup_extract_cookies, setup_select_account), but those are not competing alternatives for saving a PAT, so the guidance is sufficient.

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 (readOnlyHint=false, destructiveHint=false, openWorldHint=true), the description discloses specific behaviors: it validates and saves a session, preserves the PAT for the same account, and may prompt the user when selection is ambiguous or changes the existing account. This adds meaningful context about side effects and user interaction without contradicting the annotations.

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 three short sentences, front-loading the core action first, then providing decision rules and a key note on PAT preservation. Every sentence adds value with no fluff.

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 tool with one parameter and an output schema, the description covers the action, the precondition (after setup_extract_cookies), the decision rule for asking vs. proceeding, and the PAT preservation behavior. It lacks explicit error handling details, but the output schema likely covers return values, making it sufficiently 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?

The single parameter account_index is fully described in the schema with its source (returned by setup_extract_cookies). The tool description does not add additional meaning beyond that, so it meets the baseline for full schema coverage.

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 tool's action: validate and save a browser session after setup_extract_cookies. It identifies the resource (browser session) and the sequencing relative to a sibling, making its purpose unambiguous and distinct from setup_status, setup_extract_cookies, and setup_save_pat.

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 explicit guidance on when to use it: after setup_extract_cookies, and includes a decision rule for when to ask the user (ambiguous selection or account change) versus using the recommended account silently. It does not explicitly contrast with setup_save_pat, though it mentions PAT preservation, which could overlap, so it is not fully exhaustive.

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, but the description adds meaningful behavioral context: it explicitly states the tool does not read browser credentials or change settings, and mentions a retry behavior for admin access detection. This goes beyond what annotations alone convey, helping the agent understand side-effect boundaries.

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, each earning its place: the first states the core function, the second gives usage timing, and the third clarifies limitations. The most important information is front-loaded, and there is no redundant or filler language.

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 parameterless tool with a readOnly hint, an output schema, and three clear usage triggers, the description is complete. It covers purpose, when to use it, and what it avoids doing. The existence of an output schema means detailed return values do not need to be spelled out in the description.

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 fully covers this by defining an empty properties object. Per the baseline for 0-param tools, the description need not explain parameters. It instead focuses on purpose and behavior, which is appropriate.

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: 'Check live authentication, retry admin access detection, and get structured next actions.' This clearly identifies the tool as a diagnostic/status tool and differentiates it from siblings like setup_extract_cookies or setup_save_pat, which perform credential operations rather than status checks.

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?

Explicit usage triggers are given: 'Use before setup, after an authentication error, or when expected tools are missing.' This gives clear context for when to invoke the tool. It does not explicitly list sibling alternatives, but the closing disclaimer about not reading credentials or changing settings implies when other tools would be appropriate.

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