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

Annotations already declare readOnly and idempotent, but the description adds substantive operational context the annotations cannot convey: server-side concurrency (2 requests at a time), batch cap of 20, and quota of roughly 600/min and 2000/day per property with an explicit 'keep batches small' instruction. That is exactly the value-add expected beyond structured 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?

Output fields are front-loaded, then invocation modes, then limits. No filler sentences; even the quota sentence carries actionable guidance ('keep batches small'). It is dense but 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?

With no output schema, the description compensates by enumerating the return payload (verdict, coverage, canonical chosen vs declared, mobile usability, rich results). Combined with the quotas, batch behavior and property constraint, an agent has everything needed to call it 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 baseline is 3, but the description adds the cross-parameter constraint that every inspected URL must belong to the named property — a semantic rule absent from the individual parameter docs. It also restates the batch size limit, which the schema already caps via maxItems, so the added value is real but partial.

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?

Specific verb (inspect) plus resource (URLs) with an explicit enumeration of what is returned: verdict, coverage, robots.txt state, last crawl, canonical mismatch, mobile usability, rich results. An agent can immediately distinguish this from the sibling aggregate tools (query, opportunities) without opening a 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?

Clearly states how to choose between single (url) and batch (urls) invocation and the constraint that URLs must belong to the property; the schema even points to list-properties for property discovery. It never explicitly names a sibling as the alternative for aggregate/index-wide questions, so it falls short of full when-not routing.

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 and closed-world behavior, so the safe-read profile is covered. The description adds real value beyond that: it explains the two identifier forms, clarifies that sc-domain: spans all subdomains and protocols while URL-prefix matches exactly, and notes the permission level is returned.

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: purpose, identifier semantics, and the call-first instruction. The most actionable advice (call this first, pass the identifier) is front-loaded alongside the purpose, 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 zero-parameter, read-only listing tool with no output schema, the description covers what is returned (properties plus permission level) and the identifier formats an agent must understand to use the rest of the suite correctly. Nothing needed 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?

The tool takes zero parameters, so there are no parameter semantics to document and the baseline is 4. The description's discussion of identifier forms concerns how the output is consumed by other tools, not this tool's inputs.

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) scoped to what the authenticated account can read, and adds the returned detail (permission level). The contrast with siblings is implicit but clear: this is the enumeration tool that feeds property identifiers to every other 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?

Gives explicit sequencing guidance ('Call this first') and tells the agent what to do with the result ('pass the identifier verbatim as property to every other tool'). No exclusions are given, but there is no competing alternative for enumerating properties, so the guidance is effectively complete.

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/openWorld, so the safety profile is covered. The description adds genuinely valuable behavior: the 5000-row processing cap, the exact low_ctr threshold formula min(5%, max(1%, avg*0.75)), and the web-search-type-only restriction. It does not mention pagination or return shape, keeping it from a 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-loads the general capability, then spends exactly one clause per kind, then closes with the applicability constraint. No filler, no repetition of 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 14-parameter, no-output-schema tool the description covers purpose, kind semantics, scoping, and constraints well. It omits any hint of the return shape or the has_more pagination contract (only implied in the schema), which is a minor gap.

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% and the schema descriptions are already rich, so baseline is 3. The description still adds meaning beyond the schema, notably the low_ctr threshold formula and the "cheapest wins" framing for striking_distance that help the agent choose a kind and interpret bounds.

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+resource ("Ready-made opportunity analyses") and immediately enumerates the four analysis kinds with concrete definitions, so an agent can tell exactly what it produces versus the sibling query/question-queries tools. The "top-5000 rows of a window" scope further pins down the output.

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?

Each kind carries implicit routing guidance (e.g. striking_distance noted as "the cheapest wins"), and the "Web search type only" constraint is an explicit applicability rule. It never names a sibling alternative or an explicit when-not-to-use, so it stops short of a full 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 only cover the safety profile (readOnly, idempotent, closed-world), and the description adds substantial operational context: server-side date resolution with anchor behavior, where each filter class executes, the top-5000 sampling caveat, compare's merged-table-with-deltas contract, and the sign convention for position_change. The 'paginated sample, not an exhaustive export' warning is exactly the kind of caveat annotations cannot express.

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 purpose before moving into caveats, and each sentence carries non-redundant information (date resolution, filter execution, compare semantics, sampling). It is dense and packs several distinct rules into a single compact block, which slightly taxes parsing but wastes no words.

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 22-parameter read tool with no output schema, the description supplies the operational context an agent needs: what a row contains, how dates resolve, which filters are exact versus sampled, how compare changes the result shape, and that pagination yields a sample. Return-shape detail is minimal, but the sampling and delta semantics are the parts most likely to cause misuse and they are covered.

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?

With 77% schema coverage the baseline is 3, but the description meaningfully extends the schema: 'grouped by up to three of' dimensions, preset examples (last_28_days) with server-side resolution anchored to the last date with data, and the note that position_change requires compare and that positive means improved. It does not explain the undocumented min_clicks/min_impressions/min_position/max_position parameters, leaving a 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?

States a specific verb and resource ('Search Analytics rows for one property') and enumerates the metrics (clicks, impressions, CTR, position) and grouping dimensions, so the agent knows exactly what comes back. It never names or contrasts the sibling tools (question-queries, opportunities) that also surface Search Console data, so the boundary is inferred rather than stated.

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 concrete routing guidance: use compare instead of joining two windows ('never join two windows yourself'), and explains that value filters execute in Search Console while min/max and non-click sorts run on a top-5000 sample, which tells the agent when results are approximate. It stops short of explicit when-not-to-use-this-tool exclusions against siblings.

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 cover the safety profile (readOnly, idempotent, not open-world), and the description adds genuinely useful behavior: detection runs server-side inside Search Console, AI traffic is not labeled, these are only candidates, and results default to impressions sorting because question queries often get no click. Return format/pagination behavior is left to the schema, which is acceptable.

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 dense sentences with the core definition front-loaded, followed by mechanism, caveat, and default-sort rationale. No filler, though the parenthetical about AI features is slightly more than needed.

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 13 parameters, no output schema, and one required param, the description supplies the conceptual model (question-shaped candidates, server-side detection, AI-traffic caveat) that structured fields cannot convey. What is missing is explicit routing against the generic 'query' and 'opportunities' siblings.

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 92%, so the schema already documents nearly every parameter. The description only adds context for two of them (language relates to the question-prefix list, sort defaults to impressions), so it does not meaningfully exceed the structured 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?

States a specific resource (Google searches phrased as questions that showed this site) and explains how it is produced (Search Console regex filters built from question-prefix lists in 10 languages plus a minimum length). It implicitly separates itself from the generic 'query' sibling by describing a specialized subset, but never names the generic query tool, so an 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?

Use is implied through the framing 'raw material for FAQ pages and content that answers what people actually ask' and the note about AI features, so an agent can guess the intent. However, no explicit when-to-use / when-not guidance and no alternative sibling (query, opportunities) is named as the comparison point.

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 readOnlyHint=true and destructiveHint=false, but the description explicitly says 'submit and delete change the property' and describes a delete action. The description asserts mutation and deletion while the annotations assert a non-mutating, non-destructive tool — a direct conflict. Despite the useful --enable-writes gating detail, the contradiction with the safety annotations caps this at 1.

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 compact clause-sentences: resource definition, then the status action, then the write actions with their precondition. Information is front-loaded and no sentence is filler, though the fragment opening ('Sitemaps of a property:') is slightly terse.

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 four-action tool with no output schema, the description covers what the resource is, the per-action requirements, and the server-side write gate. It could say more about what the default list action returns, but the annotations and schema carry most of the remaining structure.

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 actionable constraint the schema cannot express: submit and delete only function when the server was started with --enable-writes, and status is scoped to a single sitemap URL. That gating information meaningfully conditions how the action parameter can be invoked.

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 (sitemaps of a Search Console property) and enumerates what it exposes: submitted files with status, errors, warnings and submitted/indexed counts. It also clarifies the multi-action surface (list, status, submit, delete). It is clear without needing sibling differentiation, since none of the listed siblings (query, inspect-url, opportunities, etc.) overlap with sitemap management.

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 states the operational conditions for the destructive/non-default actions ('action=status returns one sitemap (sitemap_url required)' and 'submit and delete ... only work when the server was started with --enable-writes'), which is useful when-to-use context for the sub-actions. It does not, however, say when to prefer this tool over siblings or when to prefer list vs status, leaving tool-selection to inference.

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