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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower. The description adds genuine context beyond annotations: it discloses the authentication mechanism (QA_MCP_STORAGE_STATE session) and the failure semantics (bounce-to-login indicates expired session). It does not describe what the report format looks like, but that is partially an output-schema concern.

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 diagnostic purpose then the trigger condition. Every clause earns its place — no filler, no restatement of the tool name.

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 2-param read-only diagnostic with full schema coverage and annotations carrying the safety profile, the description supplies everything an agent needs: what it does, how it authenticates, and when to reach for it. No output schema exists, but the description adequately frames the result (whether the page bounced to login).

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% — both parameters are fully described in the schema (url with allowlist/http-https constraint, wait_for enum with default). The description adds no parameter detail beyond what the schema provides, so baseline 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?

States a specific diagnostic verb ('navigates with the configured QA_MCP_STORAGE_STATE session and reports whether the page bounced to a login-looking path') and clearly names what it distinguishes from siblings — it's not an extraction tool but a session-health probe. An agent can tell it apart from extract_semantic_dom or session_extract without opening schemas.

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 when-to-use: 'Use when extractions unexpectedly return login forms instead of the requested page.' This gives a concrete trigger condition that routes the agent here rather than to a re-extraction. No alternative tool is named, but the trigger is unambiguous.

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 readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: the output is bounded ('a few thousand characters'), which matters for context budgeting, and the region selectors are reusable downstream. It does not cover failure modes (e.g. non-allowlisted hosts, timeouts), which the schema touches on.

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 output payload and ending on the usage directive. The first sentence is densely packed with parentheticals, but every clause carries distinct information (region types, selector handoff, table/dialog/alert contents), so nothing is wasted. Slightly heavy to parse in one pass.

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 correctly carries the return-value burden and describes the map contents well. It also explains the intended next step. It omits any mention of output size limits, truncation behavior, or error conditions for a tool that fetches an arbitrary URL, which is a minor gap for a read tool with full annotation coverage.

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 beyond the schema by linking output to input: it explains that the `selector` in each outline region is what you pass as `scope`, which is a relationship the schema alone does not convey. It adds no new detail on viewport/wait_for, hence not a 5.

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 exactly what the tool returns — a page 'MAP' of landmark regions, structured tables, open dialogs, and alert text — and enumerates the region types (header/nav/main/forms/tables/lists/dialogs). It also implicitly distinguishes itself from siblings by positioning itself as the first-pass survey before extract_semantic_dom/session_extract. An agent knows the resource and output shape 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?

It gives an explicit workflow rule: 'Start here on any page you have not seen; then extract one region.' It also names the follow-up tools (extract_semantic_dom / session_extract) and explains the handoff via the region `selector` passed as `scope`. When-to-use and the alternative path are both stated.

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, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds that it navigates to a staging URL and captures 'live state', but it discloses nothing about auth/permission requirements, rate limits, timeout behavior, or execution cost. Useful context, but thin beyond 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?

Two tightly constructed sentences: capability first, usage guidance second, no filler. Both sentences earn their place and nothing is buried.

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 does sketch the return ('factual Semantic JSON... with Playwright-native locators and live state'), which is the key thing an agent needs to interpret results. It omits the output shape details (nodes, omitted counts, context_note) that the params hint at, so it is strong but not fully self-contained.

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% across 12 params, and the schema itself carries rich per-parameter guidance (wait_for semantics, scope selector sourcing, truncation flags). The description contributes no parameter detail at all, so the baseline 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?

Specific verb ('Navigate... and return') plus a well-defined resource: Semantic JSON of interactive/test-relevant elements with Playwright-native locators. It is clearly distinguishable from extract_outline by emphasizing test-relevant elements and live state, but it never explicitly names or contrasts a sibling (e.g. extract_semantic_dom_after), 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?

'Use this before writing any Playwright test so selectors are real, not guessed' gives a clear triggering context and rationale. However it offers no when-not guidance and does not point to the obvious alternative, extract_semantic_dom_after, for post-interaction states.

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 idempotentHint=false, so safety is partly covered. The description adds substantial behavior beyond them: allowlist enforcement causing silent non-extraction, the timing-dependent uniqueness caveat for accumulating UI, and the contents of the `observed` block (navigations, xhr/fetch method/path/status, console errors, dialogs, popups) with guidance to use them for waitForURL/waitForResponse.

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-loaded with the 'Like extract_semantic_dom, but...' framing, then usage, then caveats, then the observed-block payoff. Every sentence carries information, though the prose is dense and a couple of clauses (uniqueness note, observed block) are packed into long sentences that could be split for scannability.

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 15-parameter mutation-adjacent extraction tool with no output schema, the description covers the action model, locator sourcing, allowlist constraints, timing caveats, and the shape of the returned observation metadata. Nothing an agent needs to invoke it correctly appears to be 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 description coverage is 100%, so the baseline is 3. The description goes beyond the schema by listing the declared action verbs (fill/click/press/select/goto/wait), naming the `observed` block fields for follow-up waits, and instructing where locators should come from (a prior extraction). That is meaningful semantic guidance layered on top of fully documented 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?

Names the base operation it extends (extract_semantic_dom), states the specific added behavior (executes a declared action list in the main frame first), and states what is returned (Semantic JSON of the resulting state). An agent can distinguish it from extract_semantic_dom and the session_* tools without opening a 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?

Explicitly says when to use it ('post-interaction UI a plain snapshot cannot see: success/error toasts, validation messages, opened dialogs') and how to prepare ('Derive action locators from a prior extract_semantic_dom call'). It also states the failure condition (page must remain on allowlisted hosts or nothing is extracted), which is a clear 'when this won't work' qualifier.

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, idempotentHint, and destructiveHint=false, so safety and idempotency are covered. The description adds that the output is text identical to a prompt's content, which is useful, but it does not disclose return format details, size, or any rate limits. With annotations covering the behavioral profile, a 3 is appropriate.

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?

A single, well-structured sentence that front-loads the resource and the distinguishing context. Every clause 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?

For a parameterless, read-only text-getter with annotations already covering safety and idempotency, the description is nearly complete. It explains what is returned and why the tool exists. It could be slightly more complete by noting that the content always matches the prompt, implying updates to the prompt affect this output, but that is a minor nuance.

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 parameter semantics are trivially satisfied. The baseline for zero parameters is 4, and the description adds no misleading parameter information.

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 resource (team's Playwright test-writing conventions) delivered as text, with the verb implicit in 'get'. It also relates the tool to the write_playwright_test prompt, but does not differentiate it from the sibling tools listed, which center on semantic DOM extraction and session management.

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 clearly states the condition for use: clients that do not surface MCP prompts. This is a specific, actionable when-to-use cue. However, it does not mention when not to use the tool (e.g., if prompts are available, use write_playwright_test instead), so it stops short of explicitly naming alternatives and exclusions.

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 annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so the safety profile is covered. The description adds that this is a diagnostic navigation, but says nothing about failure/timeout behavior or what 'reachable: false' means in practice, leaving room for more behavioral context.

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 with the 'Diagnostic:' qualifier front-loaded, then the purpose and the debugging use case. Zero 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?

With no output schema, the description usefully enumerates the returned frame fields, and the 2 parameters are fully documented in the schema. Only minor gaps remain — no mention of how navigation failures are surfaced or the cost/latency of loading a page.

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%, with the url allowlist/constraint and the wait_for enum documented in the schema itself. The description restates the URL concept but adds no syntax or format detail beyond the schema, so the baseline 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 description names a specific verb+resource ('navigate to a URL and return its frame tree') and enumerates the returned fields (frame_path, url, name, same_origin, reachable), which distinguishes it from the extract_* siblings that consume the tree rather than report it. It stops short of explicitly naming a sibling, so it is clear but not fully differentiated.

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 a clear use context — 'debugging cross-origin iframe boundaries before extraction' — which implicitly positions it ahead of the extraction tools. There is no explicit when-not guidance or named alternative, so it falls just short of 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 only cover readOnly/destructive/idempotent/openWorld flags. The description goes well beyond them: it enumerates what `observed` returns, states that request bodies and query strings are never captured, that dialogs are auto-dismissed and popups recorded then closed, and that leaving allowlisted hosts closes the session and halts extraction.

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-loaded with the action, then the return contract, then the locator-derivation and side-effect warnings. Dense but every sentence carries operational information; the single long paragraph is slightly harder to scan than a bulleted form would be.

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 five-parameter, nested-schema mutation tool with no output schema, the description supplies the return shape (URL/title plus `observed` categories), the locator provenance rule, the allowlist failure mode, and the extraction-folding option. Nothing essential for correct invocation 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 baseline is 3; the description still adds usable semantics by explaining that action locators should be sourced from a prior extraction's `playwright` expression and that `then_extract` defaults to a diff in the same call. It adds routing/derivation guidance rather than restating field docs.

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 (perform a declared action list of fill/click/press/select/goto/wait) on a specific resource (an open session's main frame) with scope limits (max 20). An agent can distinguish this from extraction/verification siblings 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 clear operating context: derive locators from a prior extraction and paste its `playwright` expression, pass `then_extract` to fold the snapshot into the same call, and the allowlist consequence. It does not explicitly name alternative siblings (e.g. when to prefer session_extract or extract_semantic_dom_after), so it falls just short of 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 already declare idempotentHint=true and destructiveHint=false, so the description's idempotency claim is partly redundant. However it adds real detail beyond the annotations: that closing an unknown/already-closed id succeeds and returns was_open: false — a behavioral guarantee that matters when no output schema 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?

Three short sentences, front-loaded with the action and effect, then the usage rule, then the edge-case guarantee. 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?

Covers the action, the resource released, the usage trigger, and idempotent edge-case behavior including the was_open field, which compensates for the absent output schema. It stops short of explaining where session_id comes from or what errors (other than unknown ids) can occur.

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 0% and the single parameter session_id has no description in either the schema or the description. The description implies session_id identifies a live session but gives no format, source, or example. With one parameter and no schema help, this is the minimum viable level.

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 ('Close an open session') plus the concrete effect ('release its browser context'), which clearly separates it from session_open, session_act, and session_list. 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?

'Always call this when the flow is done' gives an explicit trigger condition for use, which is stronger than most sibling definitions. It does not name an alternative or a when-not case, but for a lifecycle terminator there is no plausible alternative to route to.

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 cover the safety profile (readOnly, non-destructive, non-idempotent), and the description adds real behavioral context beyond them: truncation/omission is 'flagged, never silent', diffs are 'far smaller than a full re-extraction', the observed-behavior window between snapshots, and the diff-identity rules (frame+test-id → id → placeholder → tag+role+name) including that a renamed node appears as removed+added. The idempotentHint=false is implicitly explained by snapshot consumption. It stops short of auth/permission or rate-limit notes.

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 action and output shape, then the diff mode and its payoff, then the identity rules needed to interpret a diff. Dense but every sentence carries non-redundant information, and the long identity clause is the one piece that genuinely cannot be inferred from the schema.

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 11 parameters and no output schema, the description carries the return-value burden and largely discharges it: it names the output shape, the diff payload, the snapshot_id field, and primary_locator.playwright state validity. It leaves the full node/table/dialog output structure to the reader's knowledge of extract_semantic_dom, which is a minor gap for a tool this rich.

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, but the description adds meaning beyond the schema for the most consequential parameter: what diff_against actually returns (added/removed/changed nodes plus intervening behavior) and the identity rules that determine what counts as changed. It also clarifies that outline mode 'does not consume a snapshot id'. The remaining 9 parameters are left to their schema 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?

States a specific verb (snapshot/extract) on a specific resource (the CURRENT state of an open session), names the exact output shape (Semantic JSON) and explicitly differentiates it from the sibling extract_semantic_dom by the added `snapshot_id` and the diff capability. An agent can tell it apart from extract_semantic_dom/extract_semantic_dom_after 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 context: pass diff_against: 'previous' to get 'exactly the assertion list for the step', implying the verification-step workflow, and the schema documents outline mode as a low-cost alternative. It does not, however, state when to prefer this over extract_semantic_dom or extract_semantic_dom_after, so the alternative-selection guidance is implied rather than explicit.

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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds value beyond them by enumerating what the response contains (id, URL, expiry, counts), which matters since there is no output 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?

A single sentence that front-loads the purpose and then the payoff, with no redundant or filler clauses. Every element (diagnostic framing, resource, return fields, use case) 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 parameterless, read-only listing tool with no output schema, the description covers purpose, usage trigger, and the shape of returned data. Nothing needed 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 tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The parenthetical describes returned data rather than inputs, 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 ('list open sessions') plus the fields returned (id, URL, expiry, counts), and the 'Diagnostic' label frames intent. The verb/resource pair is distinct from session_open/session_close, though it never names a sibling explicitly.

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 a concrete trigger for use: 'recover a session id after losing context.' That is a clear usage context, but there is no statement of when not to use it or an explicit pointer to session_open/session_close as alternatives.

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 openWorldHint=false, readOnlyHint=false, non-idempotent, non-destructive. The description adds substantial context beyond that: persistent-across-calls page, fresh context per session with storageState applied if configured, idle-TTL expiry, session count cap, and allowlist re-check after every step. These are non-obvious operational constraints an agent must know, though the description doesn't cover reset/cleanup semantics explicitly.

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 purpose, then the lifecycle (open → act → extract → close), then operational constraints. Every sentence carries a distinct fact; 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?

Covers the lifecycle, state model (fresh context, storageState), lifecycle limits (TTL, cap), and security re-check — enough to call correctly without an output schema. Minor gaps remain (does the description note what session_open returns, e.g., a session id, and what triggers immediate expiration?), but for a tool with full schema coverage this is strong.

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 documents url, viewport, wait_for, and wait_selector with rich enum semantics. The description adds little parameter-level meaning (URL must be staging, allowlisted is echoed by schema), so baseline 3 is appropriate 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+resource (open a persistent browser session) with an explicit scope constraint (staging URL, MULTI-STEP flow). Clearly distinguishes itself from sibling session_act/session_extract/session_close by naming them as the follow-on workflow.

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 when-to-use ('MULTI-STEP flow') and names the exact alternatives to chain (session_act to act, session_extract to snapshot/diff, then session_close). It also implies the boundary: this is the entry point of a multi-step session rather than a one-shot extract.

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, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds that it operates on the current page without fresh navigation, which is useful behavioral context, but it does not explain what verification produces, what happens on failure, or how results are reported.

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?

A single concise sentence, front-loaded with the action and followed by key context. No wasted sentences. The opening term repeats the tool name, but the overall structure is efficient.

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?

The tool has no output schema, so the description carries the burden of explaining return values and what 'verify' yields (e.g., pass/fail per locator, resolved elements, errors). It omits this entirely, leaving an agent unsure how to interpret results, which is a significant gap for a verification 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?

Schema description coverage is 100%: the locators array documents Playwright expression syntax and session_id documents its source. The description adds no parameter-level meaning beyond what the schema already provides, 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 description names a specific action (verify_locators) and adds meaningful context (against an open session's current page, after acting, without a fresh navigation). However, it largely restates the tool name and never clarifies what 'verify' actually checks (existence, visibility, count, resolution), nor does it differentiate from the sibling tool named verify_locators.

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 parenthetical '(after acting, without a fresh navigation)' gives an implied timing condition for when this tool is appropriate, but it never names the alternative tool (e.g., verify_locators) or states explicit exclusions. Usage 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 this is a safe, read-only, idempotent, non-open-world operation, so the bar is lower. The description adds real value beyond them by disclosing the return shape (matches, uniqueness, first matched element per expression, plus a summary) and the CI drift-check scenario.

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, front-loaded with the core action, then usage and a secondary CI scenario. Dense but every clause carries information; 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?

With no output schema, the description compensates by describing what the tool returns. Combined with fully documented parameters and safety annotations, an agent has enough to call it correctly, though the relationship to session_verify_locators remains unspecified.

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 all five parameters including url, locators, viewport, wait_for, and wait_selector are already documented with defaults, enums, and constraints. The description adds no parameter-level detail beyond what the schema provides, so the baseline 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?

States a specific verb and resource: counting Playwright expressions against a live page, and notes it uses the same engine that verified the extraction. The purpose is unambiguous, but it does not explicitly distinguish itself from the sibling session_verify_locators, leaving the agent to infer the difference.

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 clear when-to-use context: 'Use after writing a test' with instructions to paste the spec's getBy*/locator expressions, and a second use case as a CI drift check. No exclusions or explicit sibling comparison are provided, but the triggering conditions are concrete.

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