GSC Maestro MCP Server

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

Annotations already establish readOnly, idempotent, non-destructive and closed-world behavior, so the bar is lower. The description still adds real value beyond them: it declares the output unit (a percent) even though there is no output schema, and the 'no external queries or stored credentials' line reinforces the closed-world hint in concrete terms.

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, formula first, then the validity constraint, then the no-side-effects note. Nothing is redundant and every sentence carries information an agent needs before calling.

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-integer arithmetic tool with full schema coverage and no output schema, the description supplies everything needed: the operation, the unit of the result, and the input-consistency requirement. There is no residual ambiguity an agent would have to resolve at call 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?

Schema coverage is 100% and both properties already document clicks and impressions as totals from one source and period. The description's consistency requirement (same source, period and filters) restates what the impressions parameter description already says, so it adds almost no new meaning. 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?

The description gives a specific verb and resource — compute clicks divided by impressions as a percent — so there is no ambiguity about what comes out. It does not name or distinguish any sibling (maestro_compare_periods, maestro_explain_search_metrics), but those perform different jobs, so the omission is minor rather than disqualifying.

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 clearly states the precondition for correct use: all numbers must represent the same search source, period and filters. It also clarifies that inputs come pre-supplied rather than being fetched. What it does not do is say when to avoid this tool or which sibling to use instead of computing CTR by hand.

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 readOnly, idempotent, non-destructive, and openWorldHint=false, and 'No API calls' largely restates that closed-world, pure-computation property. The addition of 'no saved search properties or estimated traffic' does add genuine scope context, but there is no disclosure of output shape, rounding behavior, or how percentage-point change is computed.

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, the operation and its output are stated first, and the exclusion sentence follows as a scoping caveat. No filler, no restatement of the tool name.

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 should signal what comes back; it names the key result (CTR percentage-point change) but not the full return shape or whether raw CTRs are included. For a simple four-integer pure computation that is adequate, though slightly thin on return values.

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 each parameter is already documented as nonnegative clicks/impressions in the earlier or later period. The description confirms the same framing ('caller-provided click and impression totals') but adds no format, unit, or edge-case guidance 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?

The description gives a specific verb and resource ('Compare two periods') plus the concrete computation ('CTR percentage-point changes'), and scopes the inputs as 'caller-provided click and impression totals'. It distinguishes itself from the data-fetching siblings implicitly by ruling out saved properties and API calls, though it never names them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'No saved search properties, API calls or estimated traffic' effectively tells the agent when NOT to reach for this tool (i.e., when it needs live or estimated data from maestro_public_capabilities or maestro_explain_search_metrics). The when-to-use condition — the caller already has the four totals — is clear but stated indirectly rather than by naming an alternative.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuinely useful context beyond that: 'No account access or source data' tells the agent this is self-contained reference knowledge, not a query, so it doesn't need credentials or a connected source to succeed.

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?

A single, front-loaded sentence: subject, scope, and the key caveat. Nothing is wasted and no reader has to scan for the point.

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 parameterless, read-only explainer with no output schema, the definition covers what the agent needs in order to know why and how to call it. A brief hint about when to prefer it over its sibling computation tools would make it fully complete.

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 is nothing to document and the baseline of 4 applies. The description's note that no account access or source data is needed reinforces the parameterless nature.

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 ('Explain') and the exact resources named (clicks, impressions, CTR, average position), plus the scope of the explanation (why metrics across engines shouldn't be naively combined). This distinguishes it from sibling tools like maestro_calculate_ctr and maestro_compare_periods, which compute or compare rather than define.

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: the definitional framing tells an agent to reach for this when it needs definitions or caveats rather than a computation. No explicit when/when-not guidance or named alternatives (e.g., 'use maestro_calculate_ctr for numeric results') are given, leaving routing 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 readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuinely new behavioral context beyond them: it names the data sources that are explicitly out of reach (Google, Bing, Yandex, local desktop), which prevents an agent from over-promising results.

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, and the affirmative scope statement is front-loaded ahead of the limitation. Nothing could be removed without losing 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 zero-parameter, no-output-schema explainer, the definition covers purpose and the key constraint an agent must know. A brief note on what the response looks like (e.g., a capability list vs. prose) would close the remaining gap, but it is not essential 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 tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a 0-param tool applies. No parameter-level detail is needed or missing.

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 a specific verb ('Explain') and a concrete subject ('what this hosted metrics demo does and cannot do'), so an agent can tell this is a meta/capability-inquiry tool rather than a calculation. It does not explicitly contrast itself with the look-alike sibling maestro_explain_search_metrics, leaving that disambiguation to inference.

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 can infer this should be called when a user asks about the demo's scope or whether it reaches real data. There is no explicit 'use this when' statement and no exclusion naming the sibling tools it should not be confused with.

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