MCP host-behaviour census

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

No annotations are provided, so the description carries the full disclosure burden, yet it says nothing about whether the operation is read-only, what a "design sheet" contains, or what happens if no current profile exists. The sole behavioral clue is that results derive from "the current profile," which implies a dependency but is left unexplained.

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?

There is no filler to cut, and the scope qualifier is front-loaded, but the extreme brevity is under-specification rather than efficiency. A single sentence could have stated the action and output without adding waste.

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 two undocumented required parameters, no annotations, and no output schema, the description is the only source of guidance and supplies essentially none. An agent cannot tell from this text what it will receive back or how to construct the required arguments.

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% for both required parameters, so the description must compensate and does not. "Per-server" weakly maps to host/host_version, but it never clarifies whether host_version is the server's version, the census agent's version, or something else, nor what format either expects.

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 phrase is a noun fragment that largely restates the tool name (census_design_sheet -> "design sheet"). "Per-server" and "from the current profile" add a little scope, but there is no verb saying whether it generates, fetches, or computes anything, and nothing distinguishes it from siblings like census_profile or census_verdict.

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 when-to-use, when-not-to-use, or alternative is stated among census_profile, census_sweep, census_verdict, and census_verify_profile. The only implicit hint is a precondition ("

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 supplied, so the description carries the full behavioral burden, yet it says nothing about whether the call is read-only, what authentication or permissions are needed, whether 'signed' means a cryptographic signature is returned or verified, or what side effects occur. The single sentence discloses no behavioral traits beyond the noun 'profile'.

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?

It is short, but not concise in the useful sense: it is a noun-phrase fragment with no front-loaded verb, and the brevity comes from omission rather than economy. Every word is spent on restating the 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?

For a tool with no annotations, no output schema, and zero parameter documentation, the description leaves the agent unable to determine return shape, safety profile, or parameter format. It is materially incomplete for a two-required-parameter call.

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 explain the two required parameters, but it only alludes to 'host version' without specifying format, accepted values, or how 'host' differs from 'host_version'. Neither parameter gains any meaning beyond its property name.

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 fragment 'Current signed profile for a host version' restates the tool name (census_profile) rather than stating an action; there is no verb indicating whether it fetches, computes, or validates a profile. It is marginally more informative than the name alone, but an agent cannot tell from this whether the call returns data or performs a check.

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 when-to-use guidance, no prerequisites, and no mention of the near-identical sibling census_verify_profile. An agent choosing between census_profile and census_verify_profile receives no discriminating signal from this definition.

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 behavioral burden. It does disclose one useful trait—that a mid-sweep host flip produces an INCONSISTENT result and that the profile is shim-derived—but it does not cover permissions, side effects, output shape, or how policy affects execution.

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 definition is a single front-loaded sentence with no obvious filler. Its brevity becomes under-specification, however, because key terms like 'shim-derived profile' and 'probe sweep' are compressed without explanation.

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-annotation, no-output-schema tool with three parameters at zero schema coverage, this description is far from complete. It offers a hint about inconsistency behavior but omits prerequisites, parameter roles, result interpretation, and sibling differentiation.

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, but it adds no meaningful semantics for 'host' or 'policy' and merely repeats 'host version' without format, allowed values, or role. Three undocumented parameters remain opaque.

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 states a specific action, 'Run a probe sweep,' and ties it to a 'host version,' so the basic purpose is inferable. However, 'probe sweep' is unexplained jargon, and the description does not distinguish this tool from siblings such as census_profile or census_verify_profile.

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 explicit guidance on when to use this tool versus the other census_* tools, nor any stated prerequisites. The description only implies that a sweep applies to a host version, leaving the selection context entirely 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?

With no annotations, the description carries full burden. It discloses pricing (cost, grant, subscription) but omits core behavior: whether it is read-only, what the verdict represents, side effects, or response format.

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 single sentence is compact and front-loads the purpose, but the pricing clause is less critical for tool selection and the overall phrasing is cryptic rather than efficient.

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 5 parameters, no annotations, and no output schema, the description is completely inadequate. It explains neither the parameters nor the return value, leaving an agent unable to invoke 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 coverage is 0% and the description mentions none of the five parameters (host, host_version, kind, duration_s, emits_progress). No meaning is added beyond the bare 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 restates the tool name ('Verdict query') and adds cryptic terms 'can_run / will_see_new_tool' without explaining what the tool actually does. It is vague and does not clearly distinguish from siblings like census_verify_profile or census_sweep.

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 alternatives. The only context is pricing, which does not help an agent select it.

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 supplied, so the description must disclose behavioral traits itself. It mentions the pinned trust root but says nothing about whether verification is read-only, what it returns, what happens on failure, or whether it has side effects; for a verification tool with a nested input this is a significant gap.

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 front-loaded sentence with no obvious filler; it leads with the action and object. However, its brevity is under-specification rather than inappropriate verbosity.

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 a nested object parameter, no annotations, no output schema, and no schema descriptions, the definition omits critical context: return value or verdict format, failure behavior, trust-root source, and profile schema. The one-sentence description is not sufficient for an agent to invoke the tool confidently.

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 sole parameter is a nested 'profile' object at 0% schema-description coverage, and the description adds no detail about its shape, required fields, encoding, or what constitutes a valid profile. Referencing 'a profile' does not compensate for the missing parameter documentation.

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 uses a specific verb ('Verify') and resource ('a profile') and adds the condition 'against the pinned trust root,' so the core operation is understandable. It does not compare itself with siblings such as census_profile or census_verdict, leaving ambiguity about when verification versus verdict retrieval is appropriate.

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 statement of when to call this tool, when not to call it, or which sibling to use instead. The verification wording implies a use case, but no explicit routing guidance is provided.

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