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

No annotations are given, so the description carries the full behavioral burden. It discloses useful behavior—recent messages are replayed on attach, and attaching before reproduction avoids missing messages—but omits permissions, side effects, idempotency, and whether the operation is reversible. It provides some transparency but leaves key operational traits unstated.

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 core action and followed by the key timing caveat. Every sentence earns its place with no 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 simple one-parameter schema, no annotations, and no output schema, the description covers purpose, behavior, and a critical usage caveat well. It could mention the relationship with detach or get_console for a fuller workflow picture, but it is largely complete for the attach action itself.

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%; the sole parameter target_id is fully documented as 'Target id from list_targets'. The description adds no further parameter semantics, so the baseline of 3 applies when the schema does the heavy lifting.

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 ('Connect') and resource ('WebView page'), and describes the exact effect: starting to buffer console output and uncaught exceptions. This distinguishes it from siblings like get_console (read buffered output), detach (stop), and list_targets (discover targets), even without naming 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 a clear condition for use: 'attach before reproducing an issue to be sure nothing is missed.' This tells the agent when to invoke it. However, it does not name alternatives (e.g., get_console for reading without buffering) or state when not to use it, so it falls short of the explicit when/when-not/alternatives bar.

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, the description carries the full behavioral burden. It adds valuable non-obvious context that buffered events are discarded, but it does not disclose permissions, reversibility, whether the page is closed, or the effect on other attached clients.

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?

One tight sentence with zero waste. The core action and its most important side effect are front-loaded.

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 one-parameter tool with no output schema, this covers the basic action and one key side effect. It remains incomplete about whether detaching closes the page, whether it can be reattached, and what a caller should expect afterward.

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%, and the single optional `target_id` is fully documented in the schema. The description adds no parameter-specific meaning beyond that baseline, which is appropriate here.

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 and resource: "Disconnect from a page." This is clearly the counterpart to the sibling `attach`, though it does not explicitly name that sibling or distinguish itself from `list_targets`/`get_console`.

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?

Usage is implied: call this when you want to disconnect from a page, and the note about discarding buffered events hints at a consequence. However, there is no explicit when-to-use vs. when-not guidance, no mention of `attach`, and no prerequisites.

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?

Adds substantial context beyond annotations: it discloses that execution runs with the page's full privileges, can read cookies/storage and mutate page state (consistent with destructiveHint=true), awaits promises, and explains how different return types are serialized. This is exactly the behavioral detail annotations cannot convey.

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 tightly packed sentences with zero filler, front-loaded with the core action and return contract, then privileges. Every sentence carries information an agent needs.

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 return-value burden and does so thoroughly (JSON for plain objects/arrays, short description for DOM/Map/Set/Error/window). Privilege and mutation scope are also covered, so nothing needed to call or interpret the tool 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%, so the baseline is 3; the description goes further by implying the expression parameter must be a single expression and must be wrapped in an async IIFE for statements/await. It adds no extra detail for target_id beyond the schema's own default note.

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 and resource ('Run a JavaScript expression in an attached page and return its result') and is clearly distinct from the siblings (list_targets, attach, get_console, detach). An agent can identify the tool without opening the 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 guidance ('For multiple statements or await, wrap them: (async () => { ... })()') and notes target_id defaults to the most recently attached page. It stops short of naming when-not-to-use or pointing to a sibling such as get_console for log inspection, so no explicit alternatives are offered.

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=true already establishes the safety profile, so the description's job is additive context, which it delivers: it discloses that output is buffered, that the most recent matching entries are returned (ordering/truncation behavior), and that since_seq enables incremental retrieval. It omits buffer bounds or whether old entries are evicted, which keeps it from a 5.

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 short sentences with zero filler; the core purpose is front-loaded and the incremental-fetch hint follows naturally. Every sentence 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?

For a read-only, six-parameter tool with a fully described schema and no output schema, the description covers purpose, return ordering, and the key incremental pattern. It leaves the attach prerequisite and buffer-eviction behavior unstated, which is a minor 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 100%, so levels, keyword, exclude_keywords, limit, and target_id are fully documented in the schema itself. The description only elaborates on since_seq, which is already explained in the schema, so it adds little beyond the baseline.

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 (Read) and precise resource (buffered console messages, uncaught exceptions, browser log entries) scoped to 'an attached page'. The resource is naturally distinct from siblings like attach/detach/evaluate_js, but the description never explicitly contrasts itself with them, so it stops short of a 5.

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 one concrete usage pattern: 'Pass since_seq from a previous call to get only new entries,' which is genuinely actionable for incremental polling. However, there is no when-not guidance, no prerequisites (e.g. must a page be attached first?), and no mention of alternatives, so usage is only implied.

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 declares this is a safe read. The description adds real behavioral value beyond that: it scopes the result set (WebView/Chrome pages on connected devices) and discloses the shape of what comes back (a target id per page for attach). It stops short of covering failure modes like no connected devices.

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, front-loaded with what gets listed and followed by the one fact an agent needs next (the returned target id feeds attach). 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 a zero-arg listing tool with an annotation covering its safety profile, this covers purpose, scope, and the handoff to attach without an output schema. Minor omissions (empty-result behavior, whether filtering exists) do not block 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?

The tool takes zero parameters, so the schema imposes no burden; the baseline for a no-param tool is 4. The description appropriately says nothing about arguments rather than padding with irrelevant detail.

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 ('List') and a precise resource ('debuggable H5 pages running inside Android WebViews (and Chrome) on connected devices'), and it names the follow-up sibling action ('pass to attach'). An agent can distinguish this from attach/detach/evaluate_js immediately.

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 the usage context clear implicitly by tying the output to the 'attach' step, so an agent knows to call this before attaching. It does not state when-not to use it or mention alternatives, keeping it short of full explicit routing.

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