State of Web Vitals

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds that the tool returns histogram buckets and summary stats, which is consistent and provides incremental context about output behavior. No contradictions.

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 core question. Every sentence adds distinct value: purpose, metric options, and usage guidelines. No redundancy or fluff.

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 (2 parameters, 1 required) and no output schema, the description adequately explains what the tool returns and how to use it. A brief mention of the exact structure of histogram buckets or summary stats would improve completeness, but current level is sufficient.

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%, so baseline is 3. The description adds value by clarifying that metric includes 'field CWV' or a 'scalar technique path when available,' and that filter keys are the same as get_metrics. This reinforces and slightly expands on schema descriptions.

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?

Description uses 'What is the shape of one metric?' to clearly state the unique purpose of the tool. It specifies exactly what is returned (histogram buckets plus summary stats) and lists the allowed metrics and filter options, differentiating it from sibling tool get_metrics.

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 states when not to use group_by and directs the agent to call get_metrics with group_by for comparing segments, then use get_histogram per segment. This provides clear guidance on tool selection and workflow.

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 indicate read-only. The description adds the attribution requirement and elaborates on behavior: returns aggregates, top categories for single metrics, one row per group. No contradiction with 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?

The description is well-structured with clear sections for metrics, filters, group_by. It is informative but somewhat lengthy; each sentence adds value, though some could be tighter.

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?

Without an output schema, the description hints at response structure (attribution, aggregate, top categories, groups). It covers key behavioral aspects but could detail the exact response format or error conditions.

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 schema descriptions cover 100% but the description adds rich context: lists specific metric options, explains filter keys, group_by values, and defaults. It clarifies the meaning of parameters beyond basic 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?

The description clearly states the tool aggregates Core Web Vitals and technique metrics across sites with filtering and grouping. It distinguishes itself from siblings like get_histogram (distribution) and list_options (enumerations) by focusing on aggregated numbers.

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 explains basic usage context (filter, group_by) but does not explicitly compare with siblings. It mentions attribution requirement but lacks guidance on when to use this tool versus get_histogram for distribution analysis.

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 destructiveHint=false. Description adds that it returns a list of options for other calls, providing useful behavioral context beyond 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?

Two sentences, front-loaded with action and result, no wasted words. Efficient and clear.

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 no output schema, the description adequately explains the return value (list of keys, paths, etc.). It provides context of when to use and what parameters are available. Complete for a simple discovery 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 coverage is 100% with descriptions for both params. The description adds minimal parameter info beyond mentioning an optional kind filter; it mostly focuses on the output. 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?

Description clearly states the verb 'discover' and the resource 'options for get_metrics/get_histogram', listing specific items it returns (filter keys, group_by values, etc.). It distinguishes from sibling tools by being a helper for 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?

Explicitly says 'Call this when unsure of a key or path', providing clear when-to-use advice. It does not explicitly exclude cases but the context is clear enough.

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