Mithrandir — free MCP gateway test

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

Annotations already declare read-only, idempotent, and non-destructive, and the description adds meaningful guarantees beyond those: free, isolated, synthetic, and no production account, upload, payment, or private data. This is strong behavioral context for an agent deciding whether the tool is safe to invoke.

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 compact sentences with no filler. The primary action and safety qualifiers are front-loaded, and every clause adds useful 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 single-optional-parameter demo tool with annotations covering safety, the description provides sufficient context: purpose, safety, and scenario semantics. It could be slightly more explicit about what the demo returns or how results should be used, but the wording implies a behavior-comparison demonstration.

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 for the `scenario` parameter. It lists the exact enum values ('unchanged, one-partition-changed and missing-source') and explains them as behaviors to compare, adding semantic clarity the bare enum does not provide.

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 opens with a specific verb and object: 'Run a free isolated synthetic Reuse Autopilot demonstration.' It also names the three scenario behaviors, distinguishing this demo tool from the onboarding, assess, pricing, and security-profile siblings.

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 when to use the tool: before onboarding, as a free isolated synthetic trial with no production data. It does not explicitly name alternatives or exclusions, but the 'before onboarding' framing and safety guarantees make the intended context obvious.

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 flag destructiveHint=true, readOnlyHint=false, and idempotentHint=false. The description adds that the test is 'bounded' and 'free' and mentions approving safe reads, but does not disclose what is destroyed, permission requirements, or how the required idempotency_key is used.

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, front-loaded with the purpose. The second sentence compactly lists workflow steps, though it could be broken out; no obvious filler.

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 complex 9-parameter destructive mutation tool with no output schema and 0% schema description coverage, the description is too thin. It omits prerequisites, parameter details, return behavior, and consequences of starting the trial.

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 carry parameter meaning. It hints at upstream_url ('public HTTPS MCP server') and safe_read_tools ('safe reads'), but leaves required name, policy_version, accept_terms, idempotency_key, cache_ttl_seconds, min_shadow_matches, and tool_costs_microusd semantically unexplained.

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?

Starts with a specific verb and resource: 'Start a bounded free gateway test', and outlines the workflow (connect server, approve safe reads, verify repetition). It does not differentiate from sibling tools mithrandir_demo or mithrandir_security_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?

No explicit when-to-use or when-not-to-use guidance is provided. The second sentence describes an internal sequence, not conditions for choosing this tool over the sibling tools.

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 destructiveHint false, so the safety profile is covered. The description adds valuable context by clarifying that it is a security contract description, not a claim of deployment security, which sets accurate expectations for the agent.

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-loaded with the core purpose (machine-readable description of the trust model) and then a clarifying caveat. There is no unnecessary verbosity; 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 no-parameter, read-only tool without an output schema, the description is sufficient: it states what the tool provides and warns against over-interpretation. It could specify the exact output format, but 'machine-readable' gives a reasonable hint, and the low complexity keeps this from being a major 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 has zero parameters, so the description need not explain parameter behavior. According to the rubric, a 0-parameter tool gets a baseline of 4, and the description does not introduce any confusing parameter-related language.

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 provides a machine-readable description of the v17 Cognitive Membrane trust model, listing its key components (origin-bound authority, task-scoped exact-call capabilities, replay protection, egress control, two-phase effectful actions). This is specific and distinguishes it from siblings that likely perform operations or assessments rather than describe a security model.

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 when to use it (to understand the trust model) and explicitly states what it is not (proof of vulnerability-free deployment), which suggests it is not for security auditing. However, it does not name alternative tools like mithrandir_assess or mithrandir_inspect, leaving some ambiguity about exactly which sibling to use for vulnerability checks.

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