agent-readiness

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

The readOnlyHint annotation already indicates this is a safe read operation, and the description does not contradict it. The description adds what the explanation covers, but it does not disclose additional behavioral traits such as data freshness, dependencies on prior calls, or potential error conditions. The annotation does the heavy lifting here.

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 with no wasted words. The first sentence fully defines the tool's scope and output content; the second gives a precise invocation trigger. The description is front-loaded and easy to scan.

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 an output schema, the description covers the essential context: what the tool does, what content it returns, and when to call it. Nothing important is missing for an agent to select and invoke it 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?

The input schema already documents checkId with an example, so coverage is 100%. The description adds only the context that the check belongs to the Agent Readiness Score, which is marginal extra meaning. Baseline 3 is appropriate because the schema already fully describes the parameter.

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 ('Explain'), a specific resource ('one check from the Agent Readiness Score'), and enumerates exactly what the explanation includes: what it asks, why agents care, weighting, and remediation. This clearly distinguishes it from sibling tools like list_checks, which enumerate checks, and score_site, which produces the score.

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 explicitly says to use this tool 'after score_site when the user asks why a particular finding matters.' This gives a clear trigger condition and temporal context. It does not explicitly name alternatives to avoid, so it stops short of a 5, but the usage context is strong.

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, and the description adds meaningful behavioral context beyond that: 'it installs nothing and runs no script' and 'Returns HTML to paste'. This reassures the agent about side effects and output. It does not detail auth or edge cases, but none are critical here.

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, each earning its place: purpose, eligibility condition, and safety/output note. The most important information is front-loaded with no fluff 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?

For a single-parameter, read-only tool with an output schema and annotations, the description covers when to use it, eligibility, output type, and safety behavior. Nothing an agent needs to correctly invoke 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 description coverage is 100%, and the single url parameter is already well documented in the schema. The description adds no additional information about the parameter format or constraints, so the baseline score 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?

States a specific verb and resource: 'Get the HTML snippet for a site's Agent Readiness badge'. The intended use (placing the badge on the site) is made explicit, and the operation is clearly distinct from the sibling tools explain_check and list_checks 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 clear conditions for use: 'Use when the user has a passing score and wants to display it', plus eligibility context ('Sites at grade C or better'). It does not explicitly name alternatives or say when not to use it, 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?

The readOnlyHint annotation already covers the safety profile, and the description adds a completeness guarantee with 'every check.' However, it does not disclose additional behavioral traits such as ordering, pagination, or output format, though the output schema may cover some of this.

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 with no wasted words. The action and result content are front-loaded, followed by a practical usage signal. 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?

For a zero-parameter read-only listing tool with an output schema, the description is complete: it states what is listed, the fields included, and when to use it. Nothing an agent needs to invoke 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 has zero parameters, so there is no parameter meaning to convey beyond the empty input schema. The description correctly adds no irrelevant parameter details, and the 0-parameter baseline of 4 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 uses a specific verb and resource: 'List every check in the rule set with its pillar, weight and question.' It clearly states the tool's scope and the content of the result, making it distinguishable from siblings like score_site and explain_check.

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 explicitly says 'Use when the user asks what is measured rather than how one site performs,' giving clear context for when to choose this tool. It does not name sibling tools directly, so it stops short of a full 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?

readOnlyHint=true already covers the safety profile, lowering the bar. The description adds meaningful context beyond the annotation: the 'public website' constraint sets the expectation that non-public or internal sites are out of scope, and it summarizes the analytical nature of the operation and its return payload. It doesn't disclose rate limits or runtime, but for a read-only scanner these are minor gaps.

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 with zero filler. The first sentence front-loads the verb and resource, then enumerates the output; the second sentence gives the usage trigger. Every clause 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?

Single required parameter documented at 100%, output schema present to cover return values, annotation covers the read-only safety profile, and the description covers purpose plus the exact trigger condition. There is nothing an agent needs to invoke this tool correctly that 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% — the url parameter is fully documented in the schema ('Public http(s) address, for example example.com'). The description adds only the word 'website', which marginally reinforces that the URL should point to a site rather than a generic resource. With full schema coverage, baseline 3 is correct.

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 ('Score'), a concrete resource ('a public website for agent readiness'), and enumerates the exact output payload (0-100 score, grade, fitness/adoption sub-scores, highest-value fixes). The phrase 'Use this first' plus the return-payload detail clearly distinguishes it from siblings like explain_check, list_checks, and watch_site within the same domain.

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 an explicit trigger: 'Use this first when asked whether a site is agent-ready or WebMCP-ready.' This is clear context for when to select the tool. It stops short of naming the sibling alternatives or stating when-not-to-use, so it doesn't reach full routing explicitness.

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 discloses the full behavioral flow: a confirmation email is sent, the recipient must open a link and confirm on the page, and only then are alerts sent on score or check verdict changes. The statement 'Nothing is sent without the recipient opening the link and confirming on the page' adds meaningful consent/opt-in context that goes well beyond the sparse annotations (readOnlyHint=false, idempotentHint=false).

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 three sentences with the core purpose front-loaded in the first sentence. The second sentence provides necessary process detail, and the third adds usage guidance and a consent guarantee. No filler, though the second sentence is slightly dense.

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 the essential flow: input site and email, confirmation step, and resulting alert behavior. An output schema exists, so return values need not be detailed. It does not mention prerequisites like whether the site must already be scored or what happens on duplicate watches, but these are not critical for 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 input schema already has 100% description coverage for both parameters. The description references the site and email at a high level but does not add format details or constraints beyond what the schema provides. This aligns with the baseline 3 for fully schema-covered 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?

The description opens with a specific verb+resource: 'Watch a site's Agent Readiness Score.' It clearly explains the monitoring/alerting mechanism and distinguishes itself from siblings like score_site, list_checks, explain_check, and get_badge_embed by focusing on ongoing notifications rather than one-off scoring, listing, explaining, or embedding.

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 explicitly states when to use the tool: 'Use when the user asks to monitor, track or be notified about a site's agent readiness.' However, it does not name any alternative tools or provide explicit exclusions, leaving some routing to inference given the sibling list.

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