UXMachine

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description contributes genuinely non-structured behavior: a call blocks for up to 25 seconds, and unfinished states require repeated calls. It does not disclose rate limits or failure behavior, keeping it at 4.

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 outcome (what you get back), followed by the polling instruction. The first sentence is long and clause-stacked ('with its limits, where the report is and, if an earlier measurement was given, how it compares'), which costs some readability but no sentence is wasted.

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 output schema exists, so the description must describe returns — and it does, listing status, observations, limits, report location, and comparison. Combined with the 100%-covered input schema and readOnly annotations, an agent has what it needs. Minor gap: no mention of error/not-found behavior for a bad id.

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 already 100%, so the schema carries parameter meaning; the description's added value is the polling/wait semantics ('each call waits up to 25 seconds by default'), which explains why `esperar_segundos` exists. It does not touch the `idioma` parameter, but the schema covers that fully.

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 ('Tells where a measurement stands') and resource (a measurement), and enumerates what is returned at each lifecycle stage — status, observations, limits, report location, comparison. That distinguishes it from the sibling `medir` (which starts a measurement, as the id parameter description implies), though the description itself never names the alternatives.

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 operational rule: 'While it is queued or running, call it again until it has finished,' plus the 25-second blocking default. That tells the agent how to poll correctly. It stops short of stating when-not to use it (e.g. after completion, or versus `memoria`), so not 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?

Goes beyond the annotations by disclosing the asynchronous lifecycle (id returned right away, result takes minutes, read via `estado`), the credit cost per measurement, and the no-charge behavior for failed measurements. These are meaningful traits the structured fields do not 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?

Three short sentences with zero filler; the async lifecycle and polling path are front-loaded, and the cost note is a single compact clause.

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 return-value burden and does so (an id, result via `estado`). Cost and async behavior are covered; only edge cases like comparison via `anterior` are left entirely to the schema.

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 schema already documents every parameter including the enum and the esperar_segundos polling semantics. The description only gestures at the wait/poll flow indirectly and adds no parameter meaning beyond the schema, which is the baseline-3 case.

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 (measures) and resource (a web page), plus the execution context (UXMachine, real browser). It also implicitly separates itself from the sibling 'estado' by naming it as the tool that reads the result.

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?

Clearly explains the async usage pattern — invoke, get an id immediately, then poll with `estado` — which tells the agent when this tool ends and the sibling begins. It lacks an explicit 'do not use this when...' exclusion, so it stops 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 readOnlyHint, idempotentHint, destructiveHint=false, so the safety profile is covered. The description still adds real behavioral context not present in structured data: the operation consumes no credit (cost) and returns a reconciliation of checkable vs. uncheckable findings, which tells the agent what state the site's memory is in.

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 action and its scope before the usage cue. The middle clause listing returned content is slightly baggy but each element (observed / came back / not checked) carries distinct meaning, so there is little 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 one-parameter read-only tool with no output schema, the description covers what it is, when to call it, cost implications, and the rough shape of what comes back. That is close to complete; only auth or error behavior is left unstated, which is minor here.

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?

There is a single url parameter at 100% schema description coverage, and the schema already gives format examples (https://yoursite.com or yoursite.com). The description adds nothing about the parameter, so the baseline of 3 applies when the schema does all the work.

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 a specific verb ("Reads") and resource ("the UX memory of a site") and enumerates the scope of the content: last measurement, what came back, what could not be checked. It also explicitly separates itself from the measurement sibling by stating "It does not measure," so an agent can distinguish it from medir 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?

"Call it before you start changing what users see on that site" is an explicit usage trigger, and "It does not measure and uses no credit" implicitly routes measurement work to medir. It stops short of naming the alternative tool or any other alternatives, so it is clear context rather than full when/when-not 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?

Beyond the annotations, it discloses the command's 30-minute lifetime, that it runs until self-terminating, that it should be backgrounded, and that it costs no credits — all useful operational facts an agent needs. It does not cover behavior on repeated invocations or what happens if the local port is unreachable.

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 return value, then execution guidance, then the cost note. No sentence is filler and no important detail 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?

There is no output schema, but the description explains what is returned (a runnable command) and how to use it. Combined with annotations covering the safety profile, an agent has enough to call it correctly; only edge cases like re-invocation are unaddressed.

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 `puerto`'s meaning and range and `idioma`'s enum values are already fully documented in the schema. The description mentions no parameters at all, so it adds nothing beyond the structured fields; 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 states a precise verb and resource: it returns the shell command that opens a temporary tunnel to a local server. It also ties the tool to its downstream purpose (measuring the local version with `medir`), so an agent can distinguish it from `medir` and `estado` 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 clear operational context: run the returned command in the background, it stays alive until it closes on its own 30 minutes later, and it consumes no credits. It never states when NOT to use this tool or how to choose between it and the sibling tools, so it stops short of explicit routing guidance.

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