pixelpact

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds substantial behavioral detail beyond annotations: the exact return shape includes a deviation table capped at 40 rows with an overflow note, numeric totals, pass rate, missing selectors, and the precise meaning of ok. This is rich disclosure for a tool without an output schema.

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 compact sentences with no filler. The purpose is front-loaded, followed by usage guidance, prerequisite, and return details. Every sentence contributes distinct information.

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 9-parameter tool with no output schema, the description compensates by explaining the return contents in detail, including the 40-row cap and ok semantics. Annotations cover safety and open-world behavior, and the prerequisite contractPath origin is stated. Nothing essential 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%, so the schema already documents all nine parameters, including defaults and constraints. The description only reiterates that contractPath comes from a prior extract_contract call, which is already stated in the schema description for that parameter. Baseline 3 is appropriate when the schema carries parameter meaning.

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: measures an implementation URL against a saved visual contract. It enumerates the visual dimensions checked (box position/size, computed styles, hover/focus states, pseudo-elements) and distinguishes itself from the sibling extract_contract by naming the contract as a required prior artifact.

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 when-to-use guidance: call after building or changing a UI to verify against a reference. It also states the prerequisite that contractPath must come from a prior extract_contract call. It does not explicitly compare against the sibling diff_pixels or state when not to use this tool.

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 and openWorld, so the safety profile is covered. The description adds real value beyond that: the screenshotDir precondition and the concrete return payload (percent differing pixels, threshold, ok, diff image path). It does not mention that a diff image file is written to disk as a side effect, which is a small 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?

Four sentences, front-loaded with the core action, then routing guidance, then the precondition, then the return contract. No filler and nothing redundant with structured fields.

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 10-param tool with no output schema, the description covers the essential gap: it enumerates the return values so the agent knows what a result contains, plus the precondition for the call to succeed. Nothing critical 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 each of the 10 parameters carries its own description with defaults, so the schema does the heavy lifting. The description adds no parameter-level syntax or format detail beyond it; baseline 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?

States a specific verb (renders and compares pixel by pixel) and resource (implementation URL vs. contract reference screenshot). It explicitly positions itself against the sibling check_implementation as a 'stricter visual check', so an agent can select between them without opening either 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?

Gives explicit when-to-use conditions ('after the structural check passes or when a subtle rendering difference is suspected') and names the alternative tool. It also states the prerequisite that the contract must have been extracted with screenshotDir set.

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 declare readOnlyHint=false and openWorldHint=true; the description is consistent with that, disclosing the file write to outputPath, the optional screenshot capture, and the shape of the returned summary (element count per viewport, warnings, written path). It stops short of permissions, overwrite behavior, or runtime cost for a browser-driven extraction, which is the remaining 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?

Four sentences, front-loaded with the action and side effect before the workflow constraints. Every sentence contributes routing or dependency information; only the return-summary sentence could arguably be trimmed if an output schema existed.

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 13-parameter, no-output-schema tool, the description covers purpose, ordering relative to all three siblings, the downstream screenshot dependency, and the return summary. What remains thin is handling of the many extraction-tuning parameters, though the schema documents them fully.

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 baseline is 3, but the description adds workflow meaning beyond the schema for two parameters: outputPath is where the contract JSON lands, and screenshotDir is a downstream dependency for diff_pixels rather than merely a directory. The other eleven parameters are only covered by the schema.

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 ('Extracts a visual contract from a reference URL') plus the persistence side effect ('saves it as JSON at outputPath'). It names the siblings it precedes (check_implementation, diff_pixels), so an agent can place it in the workflow 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?

Explicit ordering rule: 'Call this once per reference design, before check_implementation or diff_pixels can be used.' It also gives conditional guidance for a specific parameter ('Pass screenshotDir to also capture reference screenshots, which diff_pixels requires later'), which is exactly the when/when-not information an agent needs.

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 openWorldHint=false, and the description reinforces this with 'without opening a browser or making any network request' — consistent, not contradictory. It goes further by enumerating the returned fields (source URL, extraction time, viewports, element count per viewport, screenshot existence, extraction warnings), which is genuinely useful since there is no output schema. Minor gap: it does not say what happens when the contract file is missing or malformed.

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 tight sentences, front-loaded with the core action and scope, then the usage rationale, then the return shape. Every sentence carries information an agent would otherwise have to guess.

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 a single well-documented parameter, no output schema, and a read-only annotation profile, the description covers the remaining gaps by describing return contents and the no-network behavior. Nothing essential to correct invocation appears 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 contractPath is fully documented in the schema including its link to extract_contract, so the baseline is 3. The description adds no syntax, format, or path-resolution detail beyond what the schema already provides.

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 ('Reads a saved contract file and describes it') and adds a distinguishing negative claim: no browser, no network request. It also names the sibling tool diff_pixels and the condition linking them, so an agent can separate this from extract_contract/check_implementation without opening 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?

Explicitly gives the usage context ('Use this to inspect what a contract covers') and a concrete decision point ('before deciding whether diff_pixels is possible, since that needs screenshots to already exist'). The alternative and its precondition are stated rather than left to inference.

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