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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses blocking behavior (wait), defaults (start_url, viewport), recording capability, return structure, token TTL, and the disposable nature of sessions, which are all critical behavioral traits 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?

Description is structured and front-loaded with purpose, using a clear list for return values. It's slightly long but each sentence provides actionable information, earning 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?

Despite having no output schema or annotations, the description provides a complete picture: creation, defaults, return format, token lifecycle, disposal, and recording. It equips the agent with essentially all needed information to invoke and interpret 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?

Input schema covers all 5 parameters with descriptions (100% coverage), so the baseline is 3. The description adds some context about how parameters tie to the returned data (e.g., record for replay, wait for blocking) but doesn't extend parameter semantics significantly 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?

Description clearly states 'Create a new disposable cloud Chromium browser session on browserview.io' with a specific verb and resource. It distinguishes from sibling tools by explicitly focusing on creation and enumerating the returned artifacts (viewer_url, cdp_url, cdp_token, token_ttl_seconds).

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?

Mentions lifecycle guidance: 'Sessions are disposable; destroy them with destroy_session when done' and notes token refresh via 'get_session or mint_session_token'. This provides useful context on when to use related tools, though it doesn't explicitly state when not to use create_session.

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?

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It does so thoroughly by stating the session shuts down immediately, all connections are dropped, the session is unrecoverable, and the replay may still exist. This goes beyond a simple 'destroys the session' and provides critical consequence information.

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, describe the consequences, and provide usage guidance with a caveat. It is front-loaded with the primary verb and resource, avoiding redundancy.

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?

Given the tool's simplicity (one parameter, no output schema), the description covers the purpose, timing, effects, and an edge case (replay). It is complete in context and complements the sibling tools. No additional information is necessary.

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 input schema fully describes the single parameter (session_id) with a meaningful description. The tool description does not add parameter details, but with 100% schema coverage, the baseline of 3 is appropriate. The description's focus on the session lifecycle is sufficient.

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 destroys a browserview.io browser session permanently, using the specific verb 'destroy' and naming the resource. It distinguishes itself from sibling tools like create_session, get_session, and get_session_replay by focusing on the termination action.

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 states when to call this tool ('when the browsing task is finished to free resources'). It does not explicitly mention when not to use it or alternative tools, but the context is clear. It also notes the replay availability caveat for record:true sessions, which helps the agent understand post-destruction behavior.

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 provided, the description carries the full burden. It discloses that fetching refreshes URLs/access tokens (a side effect) and explains health fields: 'restarts (how many times the in-session browser has restarted; null if unknown) and degraded (true when the browser has restarted at least once).' It stops short of mentioning whether old tokens are invalidated or any auth/permission requirements.

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 each subsequent sentence adds useful usage or output context. The second sentence is long with parenthetical details, but it packs necessary token connection instructions without 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?

Given the simple one-parameter schema and lack of output schema, the description covers the important return elements (viewer_url, cdp_url, cdp_token, restarts, degraded) and the primary use case. It does not fully enumerate all possible response fields or error conditions, but it is sufficient for practical invocation.

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 provides 100% coverage with 'The id of the session to fetch.' The description only repeats 'by id' and does not add extra format hints or deeper parameter-specific context, so it meets the baseline for high 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 specific action: 'Fetch a single browserview.io session by id' and adds the important behavior of 'refreshing its URLs and access tokens.' It distinguishes itself from siblings like list_sessions (single vs. list) and create_session/destroy_session.

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 explicitly tells when to use this tool: 'when previously issued tokens have expired or were never captured,' and explains how to use the returned cdp_token with a header or query parameter. However, it does not explicitly mention alternatives like mint_session_token or state when not to use this tool.

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 provided, the description fully carries the transparency burden. It discloses the 'recording' status while running, the final output shape (video URL, pages timeline, event file URLs), URL expiration, timestamp alignment logic, and polling behavior with a typical finalization time. This is exemplary behavioral disclosure.

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 detailed but each sentence earns its place: purpose, prerequisite, output structure, expiration behavior, and wait behavior. It is front-loaded with the main purpose and contains no filler or repetition.

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?

Because there is no output schema, the description must explain return values, and it does so thoroughly: recording status, video URL, pages timeline with epoch-ms timestamps, per-stream NDJSON event files, ts-to-video alignment formula, URL expiration, and wait behavior. This is complete for a tool of this complexity.

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% and both parameters are already described in the schema. The description adds useful behavioral nuance (e.g., 'finalization typically takes <30s after session end') but does not add significant new meaning for the parameters themselves, so the baseline of 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?

The first sentence states a specific verb and resource: 'Fetch the replay manifest of a recorded browserview.io session.' This clearly distinguishes it from sibling tools like get_session or destroy_session, and the qualifier '(one created with record: true)' sets exact scope.

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 usage context: it applies only to sessions created with record: true, works after destruction, and explains the wait: true polling option. It doesn't explicitly name sibling alternatives, but the purpose and context make it obvious when this tool is appropriate.

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 provided, the description carries the full burden. It discloses what the tool returns (array of session summaries with listed fields) and what it intentionally omits (URLs, tokens). It does not mention pagination or rate limits, but for a simple list operation, the return shape and exclusions are the key behavioral details. This adds value beyond the schema (which is empty).

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, front-loaded with the main purpose, then lists the return fields, and finally includes a crucial exclusion with a pointer to a sibling tool. Every sentence earns its place with no redundant wording.

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?

Given the tool has no parameters, no annotations, and no output schema, the description is remarkably complete. It fully explains what is returned, what is not, and where to go for missing details. For a simple list tool, this is all the context an agent needs to select and 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?

The input schema has zero parameters, so there is no parameter detail to add. The description instead explains the return values, which is not technically parameter semantics, but the baseline for 0-parameter tools is 4 per the rubric. The description adds useful context about what is included in the response, even though it is not about 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 clearly states the action: 'List all active browerview.io browser sessions for this account.' It specifies the resource (browser sessions) and the scope (all active for the account). It distinguishes itself from sibling tools by noting this listing does not include URLs or tokens, pointing to get_session for that, which separates it from get_session and other siblings.

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 provides alternative usage guidance: 'call get_session with a session_id to get a fresh viewer_url and cdp_url/cdp_token for a specific session.' It also implicitly tells when to use this tool (when session summaries are needed) and when not to (when URLs or tokens are needed).

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?

No annotations exist, so the description carries full responsibility. It explains scopes and return values, but omits potential behavioral caveats like whether minting a new token invalidates existing tokens or whether session ownership is required. The description is honest but not exhaustive.

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 concise sentences, front-loaded with purpose, then scope definitions, then use cases and return value. Every sentence earns its place 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 tool with no output schema, the description states returned fields (token, scope, TTL) and gives enough context for correct invocation. It misses edge cases (e.g., errors, token revocation), but the core information needed is present.

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 descriptions for all three parameters. The description adds narrative context for scopes ('lets a human watch...') but largely repeats the schema's enum descriptions. No new parameter-level meaning is added beyond what the schema already provides.

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 ('Mint a new scoped access token') and the resource ('for an existing browserview.io session'). It is immediately distinct from sibling tools that create, destroy, or retrieve sessions.

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 guidance is provided: 'Use this to share a session with a person or service without exposing your API key, or to replace an expiring token.' This gives clear when-to-use context, though it doesn't mention when not to use or alternative tools (none are needed).

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