MCP CPG Agent Protocols

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

No annotations are provided, so the description bears full responsibility. It discloses the version (v3.2), lock date, and that the output is the canonical list. It does not state side effects or idempotency, but the nature (get) suggests read-only, and the detail is high for a simple retrieval.

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 sentences: one defines the resource, the second adds actionable context. Every word is necessary; no redundancy.

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 no parameters and no output schema, the description sufficiently explains what is returned (canonical list of 18 headers) and provides version context. It is complete for a simple retrieval tool, though it could mention typical use cases.

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 no parameter information is needed. Baseline is 4 per guidelines, and the description does not need to add param info.

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 the tool retrieves the GSC wire-header canon, specifically the eighteen x-gsc-* headers in canon order. It uses specific verbs and resources, and distinguishes itself from sibling tools (e.g., list_protocols, list_members) by focusing on headers.

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 usage for auditing against live GSC surfaces ('Curl-auditable against any live GSC surface'), but does not explicitly state when to use or exclude alternatives. Usage is implied rather than explicit.

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 should disclose behavioral traits (e.g., read-only). It only states the output is a 'full canon record' without mentioning side effects, permissions, or rate limits.

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 sentence with no wasted words. However, it is too brief and could benefit from a bit more structure or context.

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 retrieval tool with a small enum parameter, the description is minimally adequate. It does not explain the content of a 'canon record' or the implications of the return data.

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 already defines the parameter and its enum values. The description adds no additional meaning beyond the schema, so baseline score 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 clearly indicates the tool returns a 'full canon record' for specific protocol names, but the verb 'get' is implied rather than stated. It distinguishes from siblings by naming specific protocols, though not explicitly comparing to list_protocols.

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 use this tool versus alternatives like list_protocols or get_header_canon. The description does not mention prerequisites or exclusions.

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 provided, the description carries the full burden. It only describes what is listed (static metadata) but does not disclose behavioral traits such as side effects, rate limits, or authentication requirements. Listing is assumed read-only but not confirmed.

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 sentences, front-loading the core purpose and adding a clarifying scope note. No wasted 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?

Given no output schema, no parameters, and low complexity, the description is almost complete. It explains what is listed and the fields included. Minor gap: no mention of authentication or pagination, but acceptable for a simple list 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 has no parameters (100% coverage). The description adds meaning by enumerating the output fields (code, namespace, jurisdiction, region, GS1 territory GTIN), which the schema did not provide. This is a helpful clarification.

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 it lists '49 sovereign jurisdictional member nodes' with specific fields (code, namespace, jurisdiction, region, GS1 territory GTIN). This verb-resource combination is specific and differentiates from sibling tools like get_header_canon or list_protocols.

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 metadata only by stating 'Live supply/demand data per member is the CPG Knowledge Graph's job,' but it does not explicitly provide when-to-use or when-not-to-use guidance nor name alternatives for live data.

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 must convey behavior. It fails to state that the tool is a read operation, does not describe side effects, permissions, or return characteristics. The cryptic text adds no behavioral insight.

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 short but at the expense of clarity. It is cryptic and uses jargon without explanation, making it unhelpful. Conciseness requires effectiveness, not just brevity.

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 has no output schema, yet the description does not describe what is returned. For a listing tool, the agent needs to know the output format or content. The description is entirely inadequate for an agent to understand the tool's behavior.

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 schema is empty with 100% coverage, meaning no parameters. The description does not add meaning beyond the schema, but absent parameters, a score of 3 is baseline. The description does not explicitly confirm that no input is needed.

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 title states 'List the three GSC protocols', providing a clear verb and resource, but the description is cryptic and does not reinforce or clarify the purpose. It mentions protocol family and specific codes without explaining that the tool lists 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?

There is no guidance on when to use this tool versus alternatives. Siblings like 'get_protocol' exist but no comparison or context is given. The description does not help an agent decide when to invoke this tool.

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 bears full responsibility. It adds 'One meaning, no drift' indicating stability of signals, but does not disclose whether the operation is read-only, requires permissions, or has other behavioral traits. For a simple list operation, the description provides some context but lacks completeness.

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 extremely concise with two sentences, front-loading the enumeration of signals. No redundant information; every word adds value.

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 simplicity (no parameters, no output schema), the description is nearly complete. It lists all seven signals and adds stability context. However, it could explicitly state that the output is a list of signal identifiers, though the name and context imply 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 tool has zero parameters, and schema coverage is 100%. The description adds no parameter-specific information, which is acceptable as baseline is 4 for zero parameters. No additional value is needed beyond 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?

The description explicitly states that the tool lists all seven signals of the ACM-68000 set, naming each individually. It clearly distinguishes from the sibling tool 'resolve_signal', which likely retrieves a single signal, by focusing on enumeration of the complete set.

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 usage for obtaining all signals, but does not explicitly state when to use this tool over alternatives like 'resolve_signal'. No exclusions or prerequisites are mentioned, leaving the agent with implied but not explicit 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?

No annotations are provided, so the description must convey behavior. It indicates a read-only query returning a predefined set of six dimensions, which is sufficient for a simple list tool. No side effects are implied, but the use of 'resolves' is slightly ambiguous.

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 clear sentence, front-loaded with the core purpose. Every word adds value; no wasted text.

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 zero parameters, no output schema, and low complexity, the description covers the essential: it lists the dimensions. It could mention the return format or data type, but it is sufficiently complete given the tool's simplicity.

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 has zero parameters, so schema coverage is 100%. The description adds no parameter info, but none is needed. Baseline 4 is appropriate since parameters are absent.

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 explicitly states the tool lists the six SPARKS dimensions, using a specific verb (list) and resource (dimensions), and names each dimension. This clearly distinguishes it from sibling tools like resolve_sparks_dimension.

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 the tool is used to retrieve the list of dimensions, but does not explicitly state when to use it vs. resolve_sparks_dimension or other siblings. No exclusions or prerequisites are mentioned.

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 full burden. It only says 'Canon record' but does not disclose behavior like error handling, idempotency, authorization needs, or rate limits. The description adds minimal behavioral context beyond the basic action.

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 sentence with clear verb, resource, format, and examples. No unnecessary words. Every part 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 simple lookup tool with one parameter and no output schema, the description is adequate but missing return value details and error behavior. The agent might infer the output is a record, but specifics are absent.

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% (single parameter 'code' described as 'Member code, e.g. FR'). Description adds 'ISO-style code' and additional examples (AU, MX), improving clarity on the expected format beyond what the schema provides.

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 the tool resolves a single member using an ISO-style code (e.g., FR, AU, MX). It uses specific verb 'resolve' and resource 'member', and distinguishes from sibling list_members by implying single record lookup.

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 use for looking up a single member by code, but does not explicitly state when to use this vs alternatives like list_members or other resolve tools. No exclusions or when-not guidance is provided.

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, and the description does not disclose behavioral traits like read-only status, authentication needs, or side effects. 'Resolve' implies retrieval but is not explicit.

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 concise with a single sentence, no extraneous words. However, it lacks structure and could be more informative.

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 clarify return values. It only vaguely mentions 'state and meaning', leaving the agent uncertain about the tool's output.

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% with the parameter described as 'Signal code, e.g. ACM-451'. The description adds no extra meaning beyond the schema, earning a baseline score.

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 the tool resolves a signal code and provides its state and meaning, distinguishing it from sibling tools like list_signals which list multiple signals.

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 use this tool versus alternatives such as list_signals or resolve_member. The description does not specify prerequisites or 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?

No annotations are present, so the description carries full burden. It mentions 'canon record' but does not define what that contains, nor does it disclose any behavioral traits such as read-only status, authentication needs, or side effects. The agent is left guessing about the output.

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 very concise with one sentence, which is good for front-loading, but it omits important details (like what 'canon record' means) making it borderline under-specified. It earns its place but could be expanded slightly.

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 no output schema and no annotations, the description is insufficient. It does not explain the return format, error conditions, or prerequisites. For a simple tool with one parameter, it is minimally complete but leaves significant gaps for the 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?

The input schema has 100% description coverage, so baseline is 3. The description adds the context of 'canon record' but does not provide additional semantics beyond what the schema already states (letter or name). It is adequate but not enhanced.

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 the verb 'resolve' and the resource 'single SPARKS dimension' via letter or name, distinguishing it from the sibling tool 'list_sparks_dimensions' which would list all. It is specific but could explicitly mention the distinction.

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 is provided on when to use this tool versus siblings like 'list_sparks_dimensions'. The description only states what it does without any context about prerequisites or alternatives.

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