Browser rehearsal range for agents

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

With no annotations, the description carries the full behavioral burden. 'Capture a site mirror' implies a write/persist operation but says nothing about what is created, where it is stored, side effects, permissions, or reversibility; only 'attestation' hints at an authorization precondition.

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 with no filler, and the core action is front-loaded. The economy is good, though the parenthetical packs cryptic terms that reduce readability.

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 5-parameter tool with zero annotation coverage, no output schema, and 0% parameter documentation, the description is markedly under-specified. An agent cannot reliably know required inputs, valid values, or the difference between the fixture and public-URL modes.

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 0% across 5 parameters, so the description must compensate and largely fails. It obliquely references 'shapes', a 'public URL', and 'attestation' (mapping to url, shape, attestation), but leaves 'site' (the required param) and 'source' entirely unexplained.

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 verb+resource ('Capture a site mirror') is identifiable, but the parenthetical is opaque jargon ('fixture cooperating/external shapes') that an agent cannot decode without domain knowledge. It does distinguish the tool as a mirror-capture operation from verify_receipt or drift_check, but only weakly.

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 gestures at two modes (fixture shapes vs. a public URL with attestation), which hints at when each input form applies, but gives no explicit when-to-use/when-not guidance and never names or contrasts the sibling tools (drift_check, rehearse, verify_receipt).

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 burden, and it leaves the critical traits unknown: whether revalidation is read-only or mutates/repairs state, whether it is expensive or rate-limited, and what happens when drift is found. "Revalidation" weakly hints at a re-run check but discloses nothing concrete.

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 front-loaded sentence with no filler — efficient. The terseness is a completeness problem rather than a conciseness one.

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?

No annotations, no output schema, zero parameter documentation, and no disclosure of side effects or cost. For a tool whose name implies a potentially state-changing or expensive validation, the description is not sufficient to call it safely.

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 description never mentions mirror_id, its format, or where to obtain it. With only one required parameter the burden is light, but the description adds no meaning beyond the schema's bare string type.

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 an action (revalidation) and a scope (structural drift, one of your mirrors), but "structural drift" is unexplained jargon and it never says whether this detects, reports, or repairs drift. It is more specific than a tautology, yet an agent cannot confidently state what output or side effect to expect.

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?

There is no statement of when to call this versus the siblings (create_mirror, rehearse, verify_receipt) and no preconditions such as the mirror needing to exist or having been previously validated. The only implicit cue is that it operates on an existing mirror.

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 burden but does disclose meaningful behavior: runs are scored on prohibited effects, a pass yields a signed promotion receipt, and pricing/cost model is given. It omits failure behavior, side effects on the clone, and auth/plan prerequisites beyond cost, so it is only partially transparent.

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 purpose front-loaded ahead of the commercial detail. The pricing clause is useful but slightly dilutes focus; nothing is redundant.

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?

No annotations, no output schema, and zero parameter documentation for a 5-param tool. The description covers outcome and cost but leaves the agent without enough to invoke it correctly, particularly on mirror_id/agent/actions semantics.

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 five parameters (mirror_id, agent, actions, variant, task_class) are completely undocumented in both schema and description. The words 'workflow' and 'clone' offer only the faintest mapping to actions/mirror_id, leaving the agent to guess formats and meanings.

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 ('Rehearse a workflow against the clone') and describes the outcome ('scored on prohibited effects; a pass earns a signed promotion receipt'). It loosely ties to siblings via 'clone' (create_mirror) and 'receipt' (verify_receipt) but never names or contrasts them 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?

There is no when-to-use, when-not, or alternative guidance. The pricing sentence implies a pre-promotion rehearsal step, but the agent gets no signal on how this relates to drift_check or verify_receipt, which is exactly where routing guidance is 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?

With no annotations, the description carries the full behavioral disclosure burden. It usefully states the checks performed (scope, signature, expiry, current drift), but does not clarify whether the tool is read-only, what happens on failure, or what it returns.

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 a single front-loaded sentence with no wasted words. Its density is appropriate, though the jargon 'current drift' and 'promotion receipt' could benefit from slight expansion.

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 four required parameters, a nested receipt object, no annotations, and no output schema, this description is too sparse. It omits parameter meanings, success/failure semantics, and how it relates to sibling verification or drift tools.

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 0% for four required parameters. The description only hints at receipt contents through the listed checks and says nothing about the 'agent', 'site', or 'task_class' parameters, so it does not compensate for the schema gap.

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 and resource: 'Gate check for a promotion receipt,' and lists the verification dimensions. It does not differentiate from sibling tools, especially drift_check, which overlaps with the 'current drift' check mentioned here.

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?

There is no explicit guidance on when to use this tool versus alternatives such as drift_check or rehearse. The phrase 'gate check' implies a pre-promotion validation context, but this is left for the agent to infer.

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