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

With no annotations, the description carries the full behavioral burden and does well on two fronts: it discloses the return shape (index status, coverage, canonical, last crawl, mobile usability) and a real operational limit (Google's 2,000/day per-property quota). It stops short of stating auth/permission requirements or that the target URL must belong to the supplied verified property, both of which affect whether a call succeeds.

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, front-loaded with the operation and its scope, then return shape, then cost. Every sentence adds information. Structure is slightly fragmented by line breaks but nothing is 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 the description is not obligated to explain returns, yet it summarizes them usefully and adds the quota cost. For a two-required-parameter read operation with no annotations, that covers most of what an agent needs; the remaining gap is permission/verification prerequisites.

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 0%, so the description must compensate. 'One URL inside one property' does map the two unnamed parameters to concepts (url = the inspected URL, site_url = the containing property), but it gives no format guidance, e.g. whether site_url must be a URL-prefix or sc-domain property identifier. Partial compensation only.

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 and adds real scope: 'Run URL Inspection for one URL inside one property.' The one-URL/one-property constraint cleanly separates it from siblings like list_sites, list_sitemaps, and search_analytics, which operate at property or site level. It only lacks an explicit naming of those alternatives, which keeps it from a 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?

Usage context is implied rather than stated: a single-URL scope and a per-property daily quota hint at high-cost, targeted use, and the quota warning is a genuine invocation consideration. But there is no explicit when-to-use/when-not-to-use framing and no reference to the sibling tools, so the agent must infer the boundary.

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?

No annotations are provided, so the description carries the full burden. It does add one genuinely useful trait — the response shape (TSV top-level, compact JSON contents array) — but says nothing about permissions needed, pagination, sitemap-index handling, or whether the call is read-only, which for a bare read tool leaves meaningful gaps.

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, front-loaded with the operation and scope, the second reserved for output shape. No filler; the line break is slightly awkward but content 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?

An output schema exists, so return values need not be explained, and the description covers the essential purpose for a one-parameter read tool. Still, with zero annotations and an undocumented required parameter, an agent lacks the property-identifier format and the permission expectations it needs to call this correctly the first time.

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_url has 0% schema description coverage, so the description must compensate. "For one property" hints that the parameter identifies a property, but the critical format ambiguity (URL prefix form vs. a sc-domain-style identifier) is not resolved anywhere.

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 submitted sitemaps") plus scope ("for one property") and what the result carries (status and counts). Siblings — list_sites, search_analytics, inspect_url — operate on different resources, so confusion is unlikely even without an explicit differentiator.

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 only implied: an agent infers it should call this when it wants sitemap data for a property. There is no statement of when not to use it, no prerequisite (e.g., verification/permission requirement), and no pointer to an alternative for broader site diagnostics.

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 no annotations, the description carries the burden and does reasonably well: it implies a read-only, permission-scoped operation ('properties the account can read') and discloses the return shape ('TSV: site_url<TAB>permission_level'). It does not cover auth requirements or pagination, but for a zero-argument read-only listing the risk surface is minimal.

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, front-loaded with what is returned first and the practical follow-up instruction second. No filler or repetition.

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 no-parameter discovery tool, everything an agent needs is present: what is listed, the permission scoping, the exact output format, and how to reuse the returned values. An output schema exists, so the TSV explanation is a small redundancy rather than a 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?

The tool takes zero parameters, so the baseline is 4. The schema is fully covered and there is nothing for the description to compensate for; the note about site_url is guidance for other tools, not a parameter of this one.

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') plus the scope ('the account can read') and an extra detail (permission level). The resource is unmistakably distinct from the siblings search_analytics, list_sitemaps, and inspect_url.

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 tells the agent the downstream use: 'Use the site_url values as-is for the site_url argument of the other tools.' That is clear context for why and when to call it, though it names no exclusions or conditions under which it should be skipped.

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 no annotations, the description carries the full burden and does most of it: it discloses default date window, valid enum values, the 1..25000 row_limit bound, and — most valuable — the pagination contract ('more_may_exist: true when rows == row_limit, so paginate with start_row'). It omits auth/permission requirements and any quota or rate-limit behavior.

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 purpose leads, parameter semantics follow in a compact labeled list, and the return/pagination contract closes it out. Given nine parameters and a zero-description schema, no sentence is filler and nothing important is buried.

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, yet the description still usefully supplements it with the more_may_exist/start_row pagination rule, which is the piece an agent most needs to iterate correctly. Combined with full parameter documentation, nothing essential for calling this complex tool 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 0% across 9 parameters, so the description must compensate, and it does: it documents site_url provenance, date formats and defaults, allowed dimension values, the full filter object shape and operator list, search_type and data_state enumerations, and row_limit/start_row semantics. Nearly every parameter gains meaning absent from the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Query search analytics') plus the scope constraint ('for one property'), which immediately separates it from the sibling inventory tools. It also names list_sites as the source of site_url, giving an agent a concrete anchor for what this tool operates on.

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 prerequisite for the required parameter is stated ('site_url: property from list_sites'), which is useful routing guidance, and defaults for date range and data_state are given. However, there is no explicit when-to-use versus when-not-to-use guidance, and the sibling inspect_url is never contrasted with this tool.

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