TrustAI Verification

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

With no annotations provided, the description carries the burden. It adds meaningful context: not just what is returned, but also the server's boundary ('it never adjudicates') and that it includes what the server verifies. This goes beyond the tool name, though it doesn't discuss side effects or failure modes (still a read-only getter).

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 that efficiently front-loads the main action ('Return') and lists contents in a clear, structured manner. Every clause adds useful information with 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 the tool's simplicity (no params, no output schema), the description is complete: it explains what the tool returns, its scope (self-description), and even notes a key operational boundary. It fully covers what an agent needs to know to decide to call it.

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 is empty (0 parameters), so there are no parameter semantics to explain. Baseline is 4 as no params exist, and the description doesn't need to add anything further.

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's purpose: 'Return the TrustAI Verification MCP self-description' and enumerates specific contents (operator, server verifies, public tools, boundary, links). This specific verb+resource distinguishes it from siblings like get_health or list_checks.

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 anyone needing an overview of the TrustAI Verification MCP, but it does not explicitly compare with alternatives or state when to use this instead of sibling tools. There is no mention of exclusions or alternative 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?

With no annotations, the description carries the full burden. It discloses the deterministic self-check behavior and return contents (uptime, flag counts), plus the local-only scope. It does not mention output format or side effects, but for a read-only health check these are acceptable 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?

The description is two sentences, front-loaded with purpose, and every word adds value. No redundancy or 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?

For a zero-parameter tool with no output schema, the description covers the essential aspects: what it returns, the deterministic nature of the check, and the local-only constraint. It is complete enough for an agent to invoke 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?

The tool has zero parameters, so the baseline is 4. The description does not need to add parameter details, and there is no ambiguity about arguments.

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's purpose with a specific verb ('Return') and a concrete resource ('server health'). It distinguishes itself from sibling tools like get_descriptor and review_legal_text by focusing on health metrics.

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 context ('Local-only; no database on the path') but does not explicitly compare to alternative tools or state when to choose this over siblings. The guidance 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 carries the burden of disclosing behavior. It explicitly labels itself as informational rather than legal advice and says it includes disclaimers ('what it never claims'), which is useful context for safe use. It does not cover authentication, rate limits, or side effects, but the read-only nature is reasonably inferred.

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 concise sentences front-load the primary purpose and then add a meaningful boundary statement. No wasted words; the em-dash construction is clear.

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 informational tool with no output schema, the description explains what the tool returns and adds a critical usage caveat. It is adequate, though it doesn't specify the exact shape or list of checks returned.

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 and 100% schema coverage, so there is no parameter meaning to add. The description correctly focuses on output rather than inputs.

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 ('Return') and identifies a concrete resource ('structural checks this server performs'), plus explicitly notes what it never claims. This clearly distinguishes it from sibling tools like review_legal_text, which perform analysis rather than list server capabilities.

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 for understanding the server's internal checks and includes a strong caveat ('Information, not legal advice'), but it does not explicitly state when to choose this over siblings such as get_descriptor or get_health. No exclusions or alternative tool names are given.

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 fully carries the behavioral disclosure burden. It reveals that the tool is 'Deterministic and local', acts as a 'neutral referee', never adjudicates, and abstains on any fault rather than fabricating one. It also states it returns 'each flag with the exact passage and a plain structural observation' and is 'load-safe', providing important behavioral context.

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 thorough but somewhat long. However, every sentence adds value: it explains the two flag types, the return format, the abstention policy, determinism/localness, and distinguishes from alternative verification approaches. The structure is logical, with numbered flag types and a parenthetical clarifying what the tool does not do. Slightly verbose but not wasteful.

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 complexity (checking for two different structural flags) and the absence of an output schema, the description is remarkably complete. It explains what flags are detected, what the output includes (exact passage + observation), that it abstains rather than fabricates, and it explicitly distinguishes itself from external verification tools. An agent could use this description 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 single parameter 'text' has a schema description that already covers its purpose and constraints (legal text from any AI vendor, max 200000 chars). The tool description adds context about what the tool looks for, but not about the parameter itself, so it doesn't add meaning beyond the schema. With 100% schema coverage, baseline 3 is appropriate.

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's purpose: 'Independently review legal text produced by ANY AI vendor for the structural red-flags behind fabrication risk' and lists the two specific flag types (orphan quotations, uncited propositions). It also distinguishes from siblings by noting what it doesn't do (live citation checking, cross-validation) and pointing to alternative tools/engines.

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 explicitly says when to use (for any AI-generated legal text) and when not to: it does not perform live case-citation checking or multi-model cross-validation, pointing to the website verifier and TrustAI engine as alternatives. This gives clear usage boundaries and alternatives.

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