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

With no annotations provided, the description carries the full transparency burden. It discloses useful behavioral details, including that domains are captured on the fly and that hero images are returned 'yours first,' but it does not mention side effects, whether the URL is modified, or any prerequisites such as authentication.

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 dense, well-structured sentence that front-loads the core action and then compacts the return format efficiently. No filler or redundant repetition of the schema is present.

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?

Because there is no output schema, the description compensates by listing the main return components: side-by-side table, findings fields, first change, and hero images. It is complete enough for a simple two-parameter tool, though it omits error behavior and explicit exclusions.

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%, so the description must compensate. It does: it clarifies that 'url' is the target URL and that 'vs' takes comma-separated reference names or domains. For a two-parameter tool, this is sufficient semantic guidance.

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 ('Critique'), a resource ('a URL'), and a target ('against comma-separated reference names or domains'), making the tool's purpose unambiguous. The detailed return-value summary further differentiates it from sibling tools like search, discover, show, and measure.

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 implies when to use the tool: whenever a URL needs to be compared against reference names or domains. However, it does not explicitly state when not to use it or name alternative sibling tools for related tasks, leaving some routing decisions to the agent.

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 behavioral burden. It usefully discloses that providers run in order (local catalog, live web search, then configured commands), returns one entry per site with a short rationale, and expects downstream usage with critique. It omits details like side effects or limits, but covers the main execution behavior.

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 compact, front-loaded with the core purpose, and every sentence adds useful information. It avoids filler and fits the tool's complexity well.

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 gives a useful orientation and even references downstream critique usage, and an output schema exists. However, it leaves important gaps such as the meaning of 'n' and provider input format, and it does not explain how this tool relates to the sibling 'search' 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 0%, so the description must compensate for parameter meaning. It explains the 'intent' parameter well with examples and hints at 'providers' by describing provider ordering, but it says nothing about the 'n' parameter or how to format the providers value.

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: 'Find reference sites for what the user is building,' with concrete examples. It conveys the tool's purpose clearly, though it does not explicitly distinguish itself from the sibling 'search' tool.

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 clear context: use it to discover reference sites based on the user's building intent, and then pass the resulting domains to critique. It does not explicitly state when not to use it or contrast it with alternatives, 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?

With no annotations, the description must carry the behavioral burden. It does disclose a key trait: 'without storing it', which signals a privacy-conscious read operation, and 'localhost works' indicates local URL support. However, it omits other behaviors such as whether the URL is fetched live, how long measurement takes, or any rate limits. The disclosure is partial but not contradictory.

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. It leads with the core action ('Measure any URL'), immediately states the privacy trait, and lists the measured aspects in a compact enumeration. Every word contributes to the tool's utility; there is no redundancy or 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?

Given the tool's simplicity (one parameter, no output schema, no annotations), the description is largely sufficient. It explains what the tool measures, notes that it does not store the URL, and supports localhost. It could clarify what the agent receives as a result (e.g., a report or scores), but that is not critical for invoking the tool. Overall, it covers the essential context for correct use.

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%, so the description must explain the parameter. It states the tool measures 'any URL' and explicitly mentions localhost, giving the agent useful context about accepted values. It does not specify protocol requirements (e.g., HTTP/HTTPS) or encoding, but the single parameter is straightforward. The description adds minimal but adequate semantics for the URL 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 clearly states the tool measures any URL and enumerates specific design aspects (fonts, type scale, spacing grid, palette, contrast, hero, layout). The verb 'measure' is distinct from siblings like search, discover, show, and critique, though it does not explicitly name an alternative. The purpose is specific and unambiguous.

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 provides no guidance on when to use this tool versus alternatives. It does not mention any exclusion criteria, prerequisites, or situations where another sibling would be more appropriate. The usage is only implied by the action itself, which is insufficient for an agent to make a confident selection.

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 full burden for behavioral disclosure. It indicates a read-style search but does not state return format, pagination, or the effect of the optional 'n' parameter. No mention of safety or side effects.

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 an illustrative example. Every word earns its place, and it is easily scannable.

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 two parameters and an output schema, the description is incomplete. It does not explain the meaning or effect of 'n', nor what 'seeded domain pointers' implies. While the output schema may cover return values, parameter semantics and usage context are insufficient.

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%, so the description must compensate. It explains that the 'text' parameter is used for searching ('by text'), but provides no information about the 'n' parameter, which remains undocumented. The example hints at the text format but leaves the other parameter 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 description clearly states the action ('Find') and the resource ('stored references and seeded domain pointers') with a concrete example. It does not explicitly differentiate from siblings, but the purpose is specific and unambiguous.

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 a typical query example but provides no guidance on when to use this tool versus alternatives like 'discover' or 'show'. No exclusions or conditions are mentioned.

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, yet it only lists outputs. It does not state that the operation is read-only, what happens if the name does not match a stored reference, or whether any cached data is regenerated. For a tool named show this is a notable gap.

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 single sentence is compact and front-loads the key outputs. It earns its place, though a second sentence explaining the 'name' parameter would improve utility without harming concision.

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 tool with no output schema and no annotations, the description should cover what 'name' refers to, whether the call is read-only, and what the response contains. It only partially covers the response (summary and screenshot) and omits the rest, leaving an agent to guess.

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% and the description never explains the required 'name' property: what it refers to, how it maps to a stored reference, or expected format. The description therefore adds no semantic value for the only 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 identifies a clear deliverable — a measurement summary and hero screenshot for a stored reference — which distinguishes it from search/discover/measure/critique sibling tools. It lacks an explicit verb like 'retrieve' or 'display' but the noun phrase conveys a display/read action well enough.

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 guidance on when to call show versus a sibling, no prerequisites such as having measured the reference first, and no mention of alternatives. The phrase 'stored reference' implies the item must already exist, but that 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.