Staats

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

Beyond the readOnlyHint annotation, the description discloses key behaviors: the after-window is clamped to now, per-route pageviews are reported only if routes were recorded, and results may carry notes about truncated or uncovered windows. This goes well beyond the annotations and gives the agent actionable expectations.

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 dense, front-loaded sentences convey purpose, window behavior, conditional details, timing guidance, and result-note handling without waste. Every sentence contributes meaningful operational 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 read-only analysis tool with an output schema, the description covers the key semantics: window construction, clamping behavior, conditional per-route output, and how to handle result notes. The schema covers parameter details, so nothing essential is missing 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 documents all parameters with 100% description coverage, including defaults and provenance of annotation_id. The description adds some context about how window_days relates to before/after windows, but most of this is already present in the schema, so the added value is limited.

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 that the tool measures before/after impact of a recorded annotation in terms of visitors and pageviews. It is specific about the resource (an annotation) and the operation (comparing before vs after), though it does not explicitly differentiate itself from sibling tools like what_changed or query.

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 contextual guidance: wait a few days after shipping, and relay any notes in the result by qualifying percentages accordingly. It does not explicitly state when to prefer this tool over alternatives, but the intended use case is strongly implied by the annotation-focused language.

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 behavioral context beyond the annotations: it explains that the connection already covers the new site, that installing the script tag is the only setup, and that the response includes privacy policy wording that should be offered with owner confirmation before editing visitor-facing pages. This is valuable operational guidance not present in the 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, each earning its place: the first states the core action and deliverable, the second clarifies the connection coverage, and the third describes the response content and a recommended user-facing flow. Concise and front-loaded.

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 only 2 simple parameters, an output schema, and annotations, the description covers the essential operational details: what is created, what setup remains, and what the response includes. Nothing critical is missing for an agent to call this 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 baseline is 3. The description doesn't add parameter-specific details, but it doesn't need to because the schema already documents 'name' and 'domain' clearly. No semantic gap.

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 verb ('Create'), a clear resource ('a new site on this account'), and a concrete deliverable ('get its script tag'). This clearly distinguishes it from siblings like list_sites, update_site_context, and delete_site.

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 clearly implies when to use this tool: when creating a new site, and it adds context that no further setup is needed beyond installing the script tag. It doesn't explicitly name alternative tools or exclusion conditions, 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?

Beyond annotations (destructiveHint=true), the description discloses exactly what gets destroyed: ALL analytics data, every event and annotation. It also adds the irreversible nature and the owner-confirmation requirement, giving the agent critical safety context not present 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?

Two sentences with no filler: the first front-loads the permanent, destructive scope; the second provides the essential confirmation rule. Every word 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 purpose, irreversible data scope, and the exact confirmation requirement. With an output schema present and annotations covering destructive behavior, nothing essential for safe invocation is omitted.

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 both parameters are already documented with clear descriptions. The description reinforces the confirm semantics ('pass confirm: the site's exact domain') but does not add novel information beyond the schema, aligning with the baseline for high schema coverage.

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 the operation with a specific verb and resource: 'PERMANENTLY delete a site and ALL its analytics data (every event and annotation).' It clearly differentiates this from sibling tools like create_site and update_site_context by emphasizing irreversibility and the complete data scope.

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 strong usage precondition: 'Confirm with the owner before calling' and explains exactly what to pass as confirmation. It does not enumerate alternatives or explicit when-not-to-use conditions, but the irreversible and destructive framing implies this tool is only for permanent removal.

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?

Beyond the readOnlyHint annotation, the description discloses critical behavior: visitors only count for step N after completing step N-1, and daily identity rotation undercounts multi-day journeys. This is exactly the kind of behavioral nuance an agent needs to interpret results correctly. It adds substantial value 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?

Three sentences deliver the core definition, step semantics, caveat, and usage guidance without redundancy. The most important information is front-loaded, and 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 read-only tool with an output schema and 100% schema param coverage, the description covers the essential nuances: step ordering, step types, identity rotation bias, and when to use stored funnel steps. Nothing critical is missing for correct invocation or interpretation.

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 each parameter. The description adds meaning by explaining the step object format with concrete examples and the sequential counting condition, which is not present in the schema. It does not add much to period/from/to/site, but the schema handles those adequately.

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 identifies the tool as an ordered conversion funnel across up to 5 steps, with each step either a pageview path or custom event. This is a specific, distinct resource that differentiates it from siblings like journeys, get_overview, and query. The purpose is immediately understandable even without opening the 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?

The description gives explicit usage context: run stored funnel steps when asked how the site is doing and compare against the previous period. It also explains the daily identity rotation caveat that affects interpretation. However, it does not explicitly state when not to use this tool or name alternative tools for related 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?

With readOnlyHint=true and openWorldHint=false already in annotations, the description adds quota-status disclosure: it tells the agent to communicate approaching/grace/blocked quota and to include the upgrade link supplied in the result. This is useful behavioral context beyond the structured annotation. It also implies a comparative vs-previous-period behavior. It could have disclosed pagination or exact return-field details, but the output schema exists, so a 4 is appropriate.

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 and front-loaded: the first sentence delivers the core content list, the second adds period semantics, the third gives actionable quota guidance. Every sentence earns its place, and the most selection-relevant information appears first.

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 two-parameter read-only tool with an output schema present, the description covers what the tool returns, the key parameter behavior, and a special quota-notification requirement. It doesn't name sibling alternatives, but sibling names are visible in context. Minor gap: no explicit statement about what happens if the account has multiple sites and site is omitted. Still, completeness is high.

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 fully documents 'site' and 'period'. The description reinforces the relative-period semantics ('period: relative like...') and adds the default-value note, but it does not deeply expand beyond the schema. Baseline 3 is correct because the schema already carries the 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?

The description opens with a vivid, specific summary: 'visitor/pageview totals vs the previous period, top pages, top referrers, and a per-day series.' That names a clear verb+resource and distinguishes this overview tool from analytical siblings like funnel, journeys, what_changed, query. The title 'Site overview' is expanded into actual content dimensions, so the purpose is 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 explains the default period ('7d'), that period is relative, and that site can be omitted for single-site accounts or read from the script tag in tracked projects. It also explicitly singles out quota-status behavior and when to mention it ('approaching... while there is headroom'). It does not explicitly name alternatives or exclusion conditions versus siblings, but the context is clear enough for an agent to select it for high-level traffic overview.

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 mark the tool read-only, and the description matches that. It adds useful behavioral detail beyond the schema: the tool exposes site owner intent, data-retention settings, and well-known keys with semantic meanings, including the 'notes' convention. 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 compact and front-loads the core purpose before enumerating well-known keys. Each sentence contributes value, including the usage directive. The parenthetical about notes is slightly dense but still efficient.

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 read-only tool with an output schema and a single optional parameter, the description is largely sufficient. It tells the agent what the tool returns, what the keys mean, and when to call it. The main gap is that data-retention settings are mentioned but not elaborated, though the output schema likely covers that.

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 single parameter `site` is fully documented in the schema, including when to omit it and how to derive its value from the script tag or list_sites. The description adds no parameter-level meaning, but the schema coverage is 100%, 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 identifies the resource ('what a site is and what the owner wants from it') and the operation (retrieve context, including data-retention settings). It also lists well-known keys, making the tool's output concrete. It is clear, though it does not explicitly contrast itself with siblings such as update_site_context or list_sites.

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 explicit timing guidance: 'Read this before making recommendations.' It also explains that the notes key holds open agenda items to check at session start. It does not name alternatives or when not to use this tool, but the context is discernible.

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 goes well beyond the readOnlyHint annotation by explaining how routes are constructed: consecutive repeats are collapsed, only the first 10 steps define a route, and visitor identity rotates daily so a route describes a group, not a person. These are critical behavioral nuances not expressed in the annotations or 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?

Every sentence earns its place: core definition, usage discrimination, step syntax, route construction rules, filter guidance, and data identity caveat. The description is dense but not bloated, and the core purpose is front-loaded.

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 complexity and the presence of an output schema, the description covers everything an agent needs to correctly select and invoke it: when to use it, how steps are represented, route truncation behavior, the daily identity rotation, and filter behavior. No important gap remains.

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. The description adds meaningful semantics for the contains parameter, explaining it filters routes to those including a given path or event and suggesting how to use it for comparison. It also clarifies the step syntax that applies to contains and route interpretation.

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 and informative definition: routes visitors actually take, grouped into identical sequences and counted, busiest first. It explicitly contrasts itself with the sibling tool 'funnel', making its unique purpose immediately clear.

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 tells the agent when to use this tool: 'Use this when you do NOT already know the steps', and names the alternative funnel with its distinguishing condition. It also gives operational guidance on using the contains filter with and without to compare converting visitors.

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=true annotation already covers safety. The description adds meaningful behavioral context by stating that results are returned newest first and that period defaults to '90d', which are not visible in annotations and enrich the agent's expectations.

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 short sentences with no filler. The core resource and ordering are front-loaded, and the period default is stated in the second sentence. Every word 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 tool is simple with two optional parameters and an output schema provided. The description covers the key concept and ordering, while the schema explains site and period. Nothing essential is missing 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?

Schema description coverage is 100%, and the period default is already documented in the schema. The tool description repeats the default but adds no new meaning beyond the schema. 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?

The description identifies the resource as 'Recorded deploy/change markers' and notes the ordering 'newest first', which is specific and useful. It does not explicitly differentiate from siblings like what_changed or record_annotation, but the resource phrase is enough to convey the list operation.

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?

Usage is implied: an agent can infer that this tool retrieves annotation history. However, there is no explicit guidance on when to prefer it over alternatives like what_changed or what_broke, nor mention that record_annotation is the write counterpart.

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 annotations already declare readOnlyHint=true, and the description adds meaningful behavioral detail about what the tool returns: public site codes and ready-to-paste script tags. There is no contradiction and no missing safety-critical behavior for a read-only list operation.

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 focused sentence that front-loads the core purpose ('All sites on this account') before adding specific output details. Every word contributes value, and 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?

For a simple parameterless read-only list tool with an output schema present, the description provides sufficient context: scope and key output fields. It could be slightly more explicit about when to prefer this tool over related site-focused tools, but that gap is already covered in the usage dimension.

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 the description does not need to explain parameter meanings. The account-wide scope is stated clearly, and no filtering behavior is implied. This matches the baseline for a parameterless tool.

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 identifies the resource (all sites on the account) and the key output contents (public site codes and ready-to-paste script tags). It lacks an explicit verb like 'Lists' or 'Returns', but the meaning is unmistakable. It does somewhat distinguish itself from sibling tools by emphasizing account-wide scope, though it does not name any alternative.

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 this tool is for retrieving all sites, but it provides no explicit guidance on when to use it versus siblings like get_site_context, get_overview, or portfolio_overview. There are no when-not-to-use conditions or alternative tool references.

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 and non-open-world behavior, so the bar for additional disclosure is lower. The description adds valuable behavioral context: all sites are aggregated, shared sites are flagged, results are sorted busiest first, and the default period is 7 days. This goes beyond the structured annotations without contradicting them.

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 two tight sentences that front-load the core purpose and immediately state the most important behavioral details. Every clause adds value; there is no filler or redundant repetition of the title.

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 simple one-parameter read-only tool with an output schema, the description covers the essential behavior: scope, period, sorting, and shared-site highlighting. It does not mention pagination or data volume, but the output schema and read-only annotation reduce the need for that detail.

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 single parameter 'period' is fully documented in the input schema with examples and default. The description repeats only the default value, adding no new semantic information beyond what the schema already provides. Baseline 3 is appropriate because schema coverage is 100%.

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 that this tool returns visitors and pageviews for every site on the account, including owned and shared sites. It also specifies output details like change vs previous period, ordering, and shared-site flags, making it easy to distinguish from more narrowly scoped siblings like get_overview.

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 this is the tool for account-wide traffic metrics ('every site this account can use'), but it does not explicitly name alternatives or provide when-not-to-use guidance. An agent can infer the intended use, but the description leaves sibling differentiation to the reader.

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's read-style verb ('Break a metric down') is consistent with that, so there is no contradiction. The description adds modest behavioral context by specifying period syntax ('24h'/'7d'/'4w' style, or ISO from/to) and filter semantics, but doesn't disclose limit/pagination behavior or result shape — though an output schema exists to cover the latter.

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?

One dense sentence front-loads the core operation, followed by compact lists of metrics, dimensions, and period formats. The enum lists are slightly redundant with the schema, but nothing is extraneous and the useful period-format note 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?

Given full schema coverage and an output schema, the description need not explain return values or most parameters, and it does cover the core operation and period semantics. The notable gap is the absence of usage guidance relative to the many analytics sibling tools, which matters especially for a tool named as generically as 'query'.

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 8 parameters; the description mostly re-lists the metric and dimension enums already present in the schema. The only additive tidbit is clarifying the period format and the ISO from/to alternative, which is modest — the baseline 3 for high schema coverage 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?

Opens with a specific verb-resource-scope statement ('Break a metric down by a dimension with optional equality filters') and enumerates the allowed metrics and dimensions. The operation is clear, but it does not explicitly differentiate from analytics siblings like get_overview or funnel, so the agent must infer the boundary.

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?

No guidance on when to choose this tool over analytics siblings such as get_overview, funnel, journeys, what_broke, or what_changed. No exclusions, prerequisites, or alternatives are mentioned, leaving the agent without routing help beyond the raw sibling names.

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 makes the side effect clear (a write to the site timeline) and adds behavioral guardrails not in the annotations: one annotation per meaningful change, and commit/routes feeding compare_around's before/after reporting. Annotations already flag idempotent=false and destructive=false, so there is no contradiction.

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 first states purpose, the second gives the trigger and style rules, and the third explains optional parameters. All information is front-loaded and 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?

With full schema coverage and an output schema present, the description covers the core decision points: when to call, how to phrase text, and when to enrich with commit/routes. It could add an explicit alternative/exclusion hint, but nothing necessary for correct invocation 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 coverage is 100%, so the baseline is 3, but the description adds semantic value by explaining why commit and routes matter (they let compare_around scope before/after traffic) and by reinforcing text formatting. It does not substantially add to site or ts, but the overall contribution moves it above baseline.

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-resource pair ('Mark a moment on a site timeline') and concrete examples (deploy, content change, campaign start), plus an explicit trigger ('Call this every time you ship a change'). This clearly differentiates it from read/report siblings like list_annotations and compare_around.

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 provides a crisp when-to-use rule: every time a change is shipped, and it adds practical conventions (present-tense text, one annotation per meaningful change, include commit/routes when known). It does not explicitly list when-not-to-use or name alternatives, so it falls just short of full routing guidance.

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 annotations declare destructiveHint=true and idempotentHint=true, and the description complements that by explaining the merge semantics: fields are merged, null deletes its key, events merges per entry. It also exposes the destructive behavior of retention_days (shortening schedules permanent deletion at the nightly prune, confirm with owner first). This is meaningful behavioral context beyond the hints.

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 entire description is two dense sentences with no filler. The first sentence front-loads the core behavior (merge, null-deletes, events-per-entry), and the second sentence clarifies the one exception (name/domain update the site record). 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?

Given 10 params, 100% schema coverage, an output schema, and annotations, the description caps the missing context: merge semantics, null-delete behavior, and the destructive retention_days caveat. An agent can invoke it correctly without needing more prose; the structured fields carry the rest.

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 each parameter already has a description; the tool description adds the crucial merge/delete semantics and explicitly calls out name/domain as record-level fields. The description doesn't repeat every parameter, which is appropriate, but the merge semantic is essential and is stated. Slight deduction because the description could have summarized the event/funnel shapes slightly more, though the schema already covers them.

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 clear verb+resource ('Save or amend what a site is for') and immediately distinguishes the tool's merge behavior from a plain overwrite. It also explains that name/domain update the site record itself, which separates it from the context-field behavior and from siblings like create_site or get_site_context.

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 and the site parameter anchor the tool to an existing site ('the site's data-site code, from its script tag or list_sites'), and the schema adds explicit guidance about omitting site for single-site accounts and reading the code from the script tag in a tracked project. It doesn't explicitly say 'use get_site_context to read before updating' but the merge semantics imply an existing context.

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?

Beyond the readOnlyHint annotation, the description discloses important behavioral details: findings clear statistical floors, so an empty result is meaningful; samples are sanitized; each error is tied to the nearest deploy annotation. This tells the agent how to interpret empty versus non-empty results, which is critical for correct use.

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 dense and packed with useful detail, without filler. It is a single long sentence, but every clause adds relevant information about signal types or interpretation. It is not maximally concise due to the parenthetical-heavy structure, but it earns its length.

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 that an output schema exists and the annotations cover the read-only safety profile, the description provides sufficient context: signal categories, their fields, statistical floors, empty-result meaning, and a clear call to action. An agent can correctly decide when and how to use this 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?

The input schema already documents both parameters with 100% coverage, including the period default. The description repeats the '7d' default but adds no new parameter-level meaning beyond what the schema provides. Baseline 3 is appropriate since the schema carries the parameter documentation burden.

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 identifies the tool's purpose: surfacing signs of visitors hitting problems (JS errors and behavioral friction) in a period. It names specific signal types (new_error, error_spike, nav_loop, refresh_burst) and what each contains, making it distinguishably about breakage detection rather than generic analytics. The title and description together leave no doubt about what the tool reports.

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 an explicit, actionable usage instruction: 'Check it after every deploy.' This tells the agent exactly when to invoke the tool. It does not explicitly list alternatives or when-not-to-use scenarios, but the deploy-triggered guidance is strong and contextually sufficient.

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 mark the tool read-only, and the description adds useful behavioral context about the kind of analysis performed: statistical unusualness, referrer surges, first-time referrers, and share-of-traffic jumps. It discloses the summarization behavior without contradicting the readOnlyHint.

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 compact, front-loaded summary with a concrete list of what the tool surfaces. The trailing 'period: 7d default' is slightly redundant with the schema, but the overall size is appropriate.

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 an output schema and fully documented parameters, the description is sufficient for an agent to know what this tool returns and when to call it. It could be more complete with explicit sibling guidance, but nothing essential 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%, so the schema already documents both parameters. The description only repeats the period default and adds no new parameter semantics beyond what the schema provides; 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 names the resource (notable movements in a period) and spells out concrete output categories: unusual traffic days, referrer surges, first-time referrers, pages with jumped share, and recorded annotations. It does not use an explicit verb and does not call out a sibling differentiation, so it stops short of 5.

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 phrase 'without scanning raw numbers' gives the agent clear context for when this digest-style tool is appropriate versus looking at raw data. It does not explicitly name alternatives or state when not to use it, but the intended use case is reasonably clear.

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