QuerySail: Google Search Console

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

Annotations already declare read-only/idempotent/non-destructive, and the description corroborates without contradicting while adding substantial behavior: Pacific Time, the 'last 28 finalized days' default window, that click change is decomposed into impressions and CTR parts, that filters/search type apply to both periods, and a candid caveat that changes are observed differences and do not identify causes. This is disclosure well beyond 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?

Front-loaded with the triggering scenario, then flows from scope to comparison modes to return shape to caveats. The single dense paragraph is efficient, though it is long enough that the return-value and timezone details could be split for faster scanning.

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 comparative tool with an output schema and full annotation coverage, the description covers the decision to use it, the comparison-mode semantics, defaults, timezone, and the limits of what the output means. Nothing an agent needs to select or 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?

Schema coverage is 100%, so parameters are already documented, but the description still adds defaults and cross-parameter semantics the schema lacks: 'previous_period' as the implicit default window, the last-28-finalized-days behavior with no dates, and the rule that explicit previous dates override compare_to. Useful additive context rather than mere repetition.

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 (compares) and resource (clicks, impressions, CTR, average position for a property between two periods), and implicitly distinguishes itself from the single-period sibling get_performance by framing the whole tool around change between periods. An agent can immediately tell this is the 'what changed' tool rather than a raw metrics fetch.

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?

Opens with explicit trigger conditions ('when the user asks what changed between two periods, why traffic went up or down, or which pages/queries/countries/devices gained or lost'), and the compare_to enum plus the 'Not used with explicit previous dates' note disambiguates the comparison modes. It also references get_performance for filter format, anchoring the sibling relationship.

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 read-only/idempotent/non-destructive, and the description adds substantial context on top: Pacific Time semantics, the exact default date window, cursor-based paging with row bounds, the critical caveat that query/page breakdowns are truncated to top rows so a missing row does not mean zero, and that figures are observed values not causes.

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?

Front-loaded with the core purpose and dense with useful constraints, with no filler sentences. It is long, but nearly every clause encodes a distinct behavioral rule; a small amount of tightening would be possible.

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 an 11-parameter tool with an output schema, the description covers everything an agent needs to invoke it correctly: defaults, time zone, pagination, dimension/filter interactions, search-type semantics, and data-completeness caveats. Return-value structure is left to the output schema, which is appropriate.

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 schema already carries per-parameter detail and the baseline is 3. The description still adds meaning beyond it, notably the interaction rules (hour cannot combine with date, searchAppearance must be the only dimension, discover/googleNews have no queries) and a concrete filter example.

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?

Names a specific verb and resource ('retrieve Google Search Console search performance') and enumerates exactly what the metrics are (clicks, impressions, CTR, average position). It is immediately distinguishable from the sibling compare_performance by its stated single-property, single-period scope ('Covers one period at a time').

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 conditions for every major mode: omit dimensions for totals, add dimensions to break down, use filters to narrow, group by hour for last-hours/days analysis, and pick search_type per result surface. It also states the default window when no dates are supplied and warns that hourly is limited to the last 10 days.

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 annotations (readOnlyHint/idempotentHint already establish safety), the description discloses scope limits (1–20 URLs, single property), the important caveat that results describe the last-indexed version rather than a live test, and an explicit capability boundary ('cannot request indexing, a recrawl or change anything'). These are exactly the non-obvious behaviors an agent needs.

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?

Front-loads the trigger condition before the mechanics and return payload, and every sentence carries information. It is dense and fairly long, but the length is justified by the enumerated return fields and the live-vs-indexed caveat, so nothing reads as 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?

With an output schema present the description needn't explain returns, yet it does so usefully while also covering scope, caveats, and limits. For a 3-parameter read tool with full schema coverage, 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?

Schema description coverage is 100%, so both required parameters are already documented in the schema (including the 1–20 bounds and the property-membership requirement). The description restates the URL-count limit and the property_id constraint without adding syntax or format detail beyond the schema, so baseline 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 (runs Search Console URL Inspection for full URLs of one property) and enumerates the returned per-URL fields, which cleanly separates it from the sibling performance/sitemap/property tools. An agent can identify this tool's domain 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?

Opens with an explicit trigger list ('when the user asks whether specific pages are indexed by Google, why a page is not on Google, or which canonical Google chose'), which is clear usage context. It does not, however, name or exclude any sibling alternative (e.g. get_performance or list_sitemaps), so routing among siblings 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.

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, so safety is covered; the description adds genuinely new behavior: deduplication across connected accounts, one site name possibly matching multiple properties, and the returned permission level and connection status. It does restate read-only, which duplicates annotations, keeping it below 5.

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?

Front-loaded with the usage trigger and return summary; sentences are efficient and purposeful. The closing 'Read-only. Does not change anything' mildly duplicates annotation data but is brief.

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 rich annotations, a full output schema, and 100% parameter coverage, the description supplies what's needed to select and invoke the tool. Pagination via cursor is left to the schema, which is acceptable given the output schema exists.

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 both parameters (cursor, connection_id) are already documented in the schema. The description adds nothing about cursor pagination or connection filtering, so the baseline 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 (list Search Console properties/sites) and clarifies it returns exact property IDs, distinguishing it from siblings like list_sitemaps or get_performance. The added detail about ID formats ('sc-domain:example.com', 'https://example.com/') makes the resource concrete.

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 trigger conditions: 'when the user asks which Google Search Console sites or properties they can access, or to find the exact property_id for a site.' No explicit when-not condition or named alternative sibling, so it falls 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?

Annotations already declare readOnly/idempotent/destructive=false, so the bar is lower. The description still adds real value: the caveat that 'URL counts are listed URLs, not indexed URLs' prevents misinterpretation, and it explicitly scopes out write operations (cannot submit, resubmit or delete).

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?

Front-loads the usage trigger before the descriptive detail, and each sentence carries a distinct purpose (trigger, output shape, sitemap_index, caveat, read-only scope). Slightly dense but nothing wasted.

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?

An output schema exists, so enumerating return fields is partially redundant, but the usage trigger, index-recursion behavior, listed-vs-indexed caveat and read-only scope make the definition fully actionable for an agent.

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 restates the sitemap_index behavior ('list the sitemaps inside a sitemap index') but adds no format or edge-case detail beyond what the schema already documents.

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 ('Lists the sitemaps submitted for one property') and enumerates the returned fields, making it clearly distinct from siblings like list_properties and get_performance.

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?

Opens with an explicit trigger condition ('Use this when the user asks which sitemaps a site has... whether Google read them, or whether they have errors'), plus a second usage case for sitemap_index. It never names an alternative or a when-not condition, so it falls 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.