Bowmark

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

Although annotations already mark this as destructive and non-read-only, the description adds critical behavioral nuance: it deletes Bowmark's record and cookies, does NOT sign the account out on the site, and cannot be undone. This meaningfully goes beyond the annotation flags.

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 well-organized and appropriately sized for a destructive operation. It front-loads the core action, then covers consequences, irreversibility, and usage boundaries — every sentence carries distinct value.

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 no output schema, the description is complete: it covers what happens, what does not happen, irreversibility, when to call it, and when not to. Combined with strong annotations, nothing an agent needs to invoke it correctly is missing.

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 the single parameter `id` is already documented as 'The connection `id` from `list_connections`'. The description repeats that provenance without adding new parameter-level detail, so it meets the baseline but does not exceed it.

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 ('forget') and resource ('saved login'), and anchors the operation to the id returned by `list_connections`. It also disambiguates from the sibling `logout_connection` by explaining what the operation is not.

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 an explicit trigger condition ('Only call this when the user asked to remove a saved login'), names the exact alternative for signing out (`logout_connection`), and prohibits use on stale connections where re-authentication is the correct path.

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 far beyond the annotations by disclosing that the call is read-only, touches no site, returns a one-line index on no match, can return partial/sliced results, and has three tiers including live third-party site tools. No contradiction with annotations is present.

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 long and dense, but it is well-structured with bolded sections and a clear front-loaded usage statement. Some redundancy exists around the cheapness and one-line-index behavior, but nearly every paragraph carries actionable guidance.

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, the description fully explains return shapes, the three tiers, bounded/sliced responses, and the complete loop from `get_library` to `run`. Nothing essential is missing for an agent to use 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?

The schema already describes the single parameter well, and the description adds significant extra meaning: pass the user's words, use a hostname from a URL rather than query parameters, a rough guess is safe, and omitting the query still returns the index. This materially improves correct invocation.

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 clear, specific purpose: determine whether Bowmark can already perform a task on a live website and return the callable function library for it. The title and description align, and the behavior is concretely distinguished from generic knowledge lookup.

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 says to use this whenever a task touches a live website and for Bowmark questions, and it frames the check as cheap and never dead-ending. It also explains the follow-up workflow with `run` and what to do when nothing matches.

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 mark the tool as read-only, and the description adds meaningful behavioral detail: it returns only a URL, opening it requires the user to be signed in and confirm identity, and only the user's own browser can read the resolved value. This is security-relevant context beyond what readOnlyHint provides.

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. The first sentence states the function and a concrete use case; the second adds the critical return-type and security behavior. 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 one-parameter, read-only tool with strong annotations, the description fully covers what the tool returns, the authentication requirement, and the user-specific access model. Since there is no output schema, the explicit statement that it returns a URL is valuable and sufficient for an agent to invoke and interpret the result.

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 single `name` parameter is already documented as the secret's name as shown by list_secrets. The description adds only a mild constraint ('one stored secret this account holds') but no new format or validation detail, which matches the baseline of 3 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 states a specific verb and resource: return the dashboard link for one stored secret. It also distinguishes itself from value-returning siblings by explicitly promising 'a URL, never a value,' so an agent can tell it apart from tools like request_secret or list_secrets.

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 context: use this when the user wants a navigable link to one of their stored secrets, such as answering 'where is my Acme password?' with somewhere to go. It does not explicitly name alternatives or say 'not when the secret value itself is needed,' so it stops short of a 5, but the URL-versus-value contrast provides strong guidance.

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 destructiveHint=false, so safety is covered. The description adds behavioral context: that live connections allow scripts to reach signed-in pages without sign-in steps, and that needing reauth explains pauses. However, it doesn't detail the exact return format, which could be a gap, but the extra context is valuable beyond 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 two paragraphs, each with a clear purpose: first defines the output, second explains usage and exclusions. It is front-loaded with the core function. Slightly verbose with the URL and extra clarifications, but each sentence adds value, so no waste.

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, read-only list tool, the description covers what is returned, the meaning of statuses, and how to interpret results for scripts. It also clarifies limitations (adding logins is user-side). Without an output schema, it explains return fields adequately. Small gap: doesn't mention any pagination or limits, but for a likely small list this is acceptable.

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 are no parameter semantics to add. The description focuses on the output and usage, which is appropriate. Since there are no params, the baseline is 4, and the description meaningfully explains the return fields.

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 lists saved logins and enumerates the information included (id, site, account, status, last use), with a specific verb and resource. It distinguishes itself from siblings by explicitly mentioning it lists existing connections, not creating or deleting them.

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?

Provides explicit guidance on when to use (before a task needing an account) and what the statuses mean ('needs_reauth' or 'expired' causes pauses). It also clarifies that adding a new login is the user's responsibility and points to the dashboard, preventing confusion with delete_connection.

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 destructiveHint=false. The description adds the critical behavioral trait that no value is ever returned and no endpoint returns one, which is essential for an agent to avoid expecting secrets. It also specifies exactly what fields are returned. This adds significant transparency beyond 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 two short paragraphs. The first sentence states the purpose and returns, the second adds usage guidance. Every sentence is informative with no redundancy. It is front-loaded with the core action and constraint.

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 list tool with no parameters, the description is complete. It describes the output fields, the constraint on never returning values, and usage guidance with an example. No output schema exists, so the description carries the burden, which it does effectively.

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 the schema already covers all parameters (none). The description adds no parameter details because none exist. Baseline 4 is appropriate for a parameterless tool.

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 'List the stored secrets this account holds, by NAME' and enumerates the returned fields, explicitly noting it never returns a value. It also differentiates from sibling request_secret by ordering. This is a specific verb+resource that distinguishes the tool.

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 instructs 'Call this BEFORE request_secret' and explains the rationale (avoiding sending user to a page for nothing). It also gives script usage example. This clearly guides when to use this tool versus the key alternative.

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 declare destructiveHint and idempotentHint, but the description adds essential detail: Bowmark drops cookies, ends the site session if supported, and keeps the login with status logged_out. It also explains the meaning of siteSignedOut: true, going well beyond the structured 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 compact and well-structured: the first sentence states the action and id source, followed by behavioral details and usage guidance. 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 single-id tool with no output schema, the description explains side effects, the site logout capability, the meaning of the response fields, and the distinction from delete_connection. Nothing an agent needs to call it correctly is missing.

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 the single id parameter at 100% with a description that already states it comes from list_connections. The tool description repeats this source but adds no new semantics beyond that, so the baseline 3 is appropriate 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 states a specific verb ('Sign a saved login out') and resource (saved login/connection), and explicitly contrasts it with delete_connection, distinguishing it from siblings. The first sentence names the action and the identifier source, making the purpose 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 explicitly states when to call it ('Call this when the user asks to sign out of a site') and identifies the alternative tool (delete_connection) with its different outcome (forgets the entry, leaves the site session alive). This gives clear guidance on 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?

With no informative annotations, the description usefully discloses that this records feedback only and has no retry behavior. It could add detail about side effects or permissions, but it provides materially more transparency than the raw 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?

Three tight sentences front-load the purpose, then provide the runId conditional and a no-retry warning. There is no filler or repetition of schema 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 low-complexity 2-parameter tool with an output schema, the description covers purpose, parameter conditions, and behavioral boundaries. Nothing essential is missing for correct 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?

Schema coverage is 100%, so a baseline of 3 applies. The description adds value by explaining when runId should be present or omitted, which goes beyond the schema's generic 'Optional runId returned by run'.

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 action ('Record what was missing, wrong, or incomplete') and a clear resource (feedback for Bowmark to build). The title and description together distinguish this from run and get_library by framing it as a feedback-only operation.

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 conditions: pass runId when reporting on a run, omit it when get_library did not cover the task, and do not use this to retry a run. This directly routes an agent among the sibling tools and states a when-not.

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?

Discloses crucial behaviors beyond annotations: browser-side encryption, transcript/log exposure, refusal of non-human-readable names, and host-slot enforcement. None of these are visible in the schema or 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?

Front-loads the core mechanism, then uses bold directives for the two most safety-critical instructions. Despite length, every sentence earns its place by adding security, naming, or usage guidance.

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?

Provides outcome (a link), user journey, lifetime range, preconditions, validation rules, and failure behavior. No output schema exists, but the return value is described sufficiently for 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?

Schema already covers all three parameters, so the baseline is 3. The description adds meaning for name (user-facing heading, months-later list row, naming refusals) and hosts (worth passing, refused elsewhere), though type semantics remain only in 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?

States a specific action: create a named empty secret slot and return a user-facing fill-in link. This clearly distinguishes it from lookup/listing siblings like list_secrets and get_secret_link.

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 preconditions: call list_secrets first and reuse an existing set secret, and instructs the agent to hand the link to the user rather than collect the secret. It does not explicitly compare with get_secret_link, so it loses a point.

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 declare a non-readonly, open-world, destructive, non-idempotent operation, and the description goes well beyond that: it documents the four `status` values and their meanings, how `partial` must be reported, the `fixable` flag, `needs_user` handoff semantics, the hard sandbox CPU/memory/wall-clock limits, and the ~55s per-call budget. It also discloses money/cost behavior for `delegate`/`browser_agent` and the shared-vs-dedicated nature of egress IPs. No statement contradicts 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 core guidance is front-loaded and each major section is clearly headed, which is appropriate for a general code-execution tool. However the body is very long and packs in full documentation for adjacent capabilities (`delegate`, `browser_agent`, `egress.lease`) that arguably belong in those tools' own definitions, diluting focus on `run`. A meaningful share of the text is tangential rather than earning its place here.

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 an output schema exists, return values need no extra explaining, yet the description still covers status semantics, failure recovery, budget/composition limits, egress behavior, and saved secrets. For a high-complexity, open-world execution tool this is as complete a briefing as an agent could need before calling 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?

Schema coverage is 100% and the schema already carries an inline `script` example, so 3 is the baseline. The description adds genuine meaning beyond the schema: `script` is the ONLY argument (there is no `site` argument), it must be a plain async body rather than a wrapping function, `return` gets JSON-serialized back, and `log()` produces ordered log lines. That clarifies invocation in ways the schema does not.

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 opening states a specific verb, resource, and scope: it executes an authored JavaScript script against the `bowmark` global on live sites and returns a defined shape (`{ ok, result, logs, error, ms }`). It positions itself precisely against its closest sibling by directing the agent to `get_library` FIRST as the vocabulary source while framing this tool as the execution/how-to layer. An agent can distinguish `run` from `get_library` or `report` without opening any 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?

It gives explicit when-to-use and when-not-to: call `get_library` first, default to ONE capability call per script, use `Promise.all`/`allSettled` rather than sequential awaits, and use `bowmark.delegate` or `browser_agent` only for work the library does not cover (with `delegate` explicitly excluded for simple site reads). It also names the conditions that select each alternative and spells out the `needs_user`/`partial` recovery branches.

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