Nimo

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

Annotations already indicate readOnlyHint=false and openWorldHint=true, so the mutation nature is known. The description adds valuable context beyond the annotations: it consumes one free check, requires no account, and returns a private accessToken. It also instructs not to poll, which is a behavioral trait not in 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?

Three sentences with no filler: purpose first, then return info and usage, then constraints. Every clause adds necessary information for correct selection and invocation.

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 single parameter, existing output schema, and accurate annotations, the description covers lifecycle (start, read via get_check), resource consumption, account requirements, and polling prohibition. Nothing an agent needs to call 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 description coverage is 100% and already explains the 'url' parameter with an example. The description adds 'public webpage' but the schema also says 'Public page address', so no additional semantic meaning beyond the schema is provided. Baseline of 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?

The description states a specific action ('Start') and resource ('speed check of one public webpage'), and contrasts with the sibling tool by naming that it returns jobId/accessToken for get_check. This makes the tool's purpose distinct from compare_checks and get_check without ambiguity.

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 tells the agent to use get_check to read the result and warns not to repeat to poll, which provides clear invocation guidance. It does not mention compare_checks, but that tool's purpose is evidently different; the core usage context is well defined.

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/closed-world, so safety is covered. The description adds genuinely useful behavioral context beyond them: no new check is started, and both results must still be unsaved/available, which is a real operational constraint. It could say more about how long results remain comparable.

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 short, front-loaded sentences; the core action comes first, followed by the source of inputs, the non-side-effect guarantee, and the precondition. 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?

With an output schema present, return values need not be explained, and the description covers prerequisites, input origin, and the no-new-check behavior. The 'must still be available' constraint could be sharpened (how long, what happens otherwise) to be fully complete.

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 each nested field (jobId, accessToken) is already documented with origin and secrecy guidance. 'Uses the handles from check_website' largely restates what the schema already says, adding little new meaning, 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 ('Compare two completed checks of the same page and device, before and after a change') and immediately distinguishes itself from check_website by clarifying 'No new check is started.' An agent can tell this apart from starting a check or fetching a single check without inspecting 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?

Gives clear context for use (before/after a change, using handles from check_website) and a meaningful precondition ('Both unsaved results must still be available'). It does not explicitly name what to use instead when results are no longer available, so it stops short of 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?

The description adds meaningful behavior beyond the annotations: it will not consume additional checks, pending requires a 5-second wait, and completed results include measurements, suggested fixes, and a save link. This is helpful operational context that annotations alone do not provide.

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 no filler. The core read behavior is front-loaded, followed by a key behavioral note and expected result contents. 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?

The description covers invocation context, polling behavior, and result contents. Combined with a complete input schema, a detailed output schema, and informative annotations, nothing essential is missing for an agent to call this 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?

Schema description coverage is 100%, so the parameters are already fully documented with value patterns and security guidance for accessToken. The description does not add parameter-level detail beyond what the schema provides, so the baseline of 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?

The description uses a specific verb and resource: 'Read the status and result of a check_website call.' It clearly differentiates itself from check_website by stating it does not start work, so an agent can distinguish this polling/read tool from its sibling.

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 tells the agent to use this tool after a check_website call, provides the pending polling cadence ('wait 5 seconds'), and states that it does not trigger new work. It does not explicitly contrast with compare_checks, but the context is clear enough for selecting this tool.

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