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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose the scope of checks and the Dataverse dependency, but it does not explicitly state whether the audit is read-only, what permissions are needed, or whether any changes are made, leaving some safety-related behavior opaque.

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 long and front-loaded with the action verb. The first sentence is dense but information-rich, enumerating the specific checks concisely; the second gives a clear use case. No filler or unnecessary 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?

The description covers the tool's check types and intended use, and the schema handles parameter details. However, there is no output schema and the description does not describe what the audit returns or how results are structured, which is a notable gap given the absence of an output schema.

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, and the schema's parameter description already explains the default services and the Dataverse requirement. The tool description reinforces the Dataverse dependency but adds little beyond what the schema already 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 uses the specific verb 'Audit' and clearly identifies the resource as the organisation's AI attack surface using Maester's AIAgent checks (MT.1113–MT.1122). It lists concrete check categories, which distinguishes it from the more general sibling tool run_maester_tests.

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 explicitly states its intended use: 'Use this to let an AI agent police the org's *other* agents and MCP servers.' It also mentions the Dataverse service requirement. However, it does not explicitly say when not to use it or name alternative tools for general Maester tests.

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 the burden. It conveys that the operation is a read-only 'list' and indicates the returned data structure (descriptions and remediation). However, it does not mention error handling, assumptions about the results file, or any side effects, though the verb implies safety.

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 that conveys all essential information without unnecessary words. Every phrase 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 list tool with no output schema, the description adequately covers the purpose, the input file, and the optional filter, and hints at the output content. It could be slightly more explicit about the return format when no failures exist, but overall it is sufficient for this complexity level.

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%, and the description adds context by mentioning the optional category filter. It does not provide new syntax or format details beyond the schema, so it meets the baseline without adding significant parameter semantics.

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 ('List') and resource ('failed tests from a results file') and clarifies that results include descriptions and remediation, optionally filtered by category. This clearly distinguishes it from sibling tools like get_test_detail, which focuses on a single test.

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 provides clear context: it is used to list failed tests from a results file, with an optional category filter. It does not explicitly name alternatives or exclusions, but the context is unambiguous enough for an agent to know when to invoke 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?

With no annotations provided, the description carries the full burden. It clearly states the tool parses a file and produces a summary, implying a non-destructive read operation. It lacks explicit mention of error handling or file requirements, but for a simple parsing tool, the behavioral description is adequate and transparent.

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, information-packed sentence followed by a brief usage cue. It is front-loaded with the action and resource, lists key outputs efficiently, and contains no 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 one-parameter parsing tool, the description is complete: it specifies the input file, the output structure, and its place in the workflow relative to siblings. No output schema exists, but the description enumerates the return components, so the agent knows what to expect.

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 already covers the sole parameter (resultsFile) at 100%. The description adds value by linking the file to the output of run_maester_tests ('Maester results file') and framing it as the post-run summary step, which enriches the parameter's meaning 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 states a specific verb ('Parse') and resource ('a results file'), and enumerates the output components (overall pass rate, per-category breakdown, sorted critical/high failures, top failures). It clearly distinguishes itself from siblings like run_maester_tests (which runs tests) and get_failed_tests (which likely lists failures).

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 explicitly recommends when to use it: 'Good first call after run_maester_tests.' This provides clear context and a suggested workflow. However, it does not name alternatives or state when not to use it, so it falls short of the top score.

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 the burden. It discloses what data is returned (description, result, remediation, help URL, severity) but does not explicitly state that it is a read-only operation, error behavior, or that it reads from the given results file. For a simple getter this is adequate but not rich.

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, well-structured sentence that front-loads the action and includes the key fields returned. 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 there is no output schema, the description appropriately lists the return fields in enough detail for a simple getter. It does not mention edge cases like not-found errors, but for a straightforward tool this is sufficient.

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%, so parameters are already well-documented. The description adds no extra meaning to the parameters beyond the schema, so 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 uses a specific verb 'Get' and identifies the resource as 'test' with a clear identifier ('by ID'), plus enumerates the fields returned. This clearly distinguishes it from sibling tools like get_failed_tests (which lists tests) and run_maester_tests (which runs tests).

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 makes it clear this is for retrieving details of a single test by ID, which implies use when you need full information for a specific test. It does not explicitly mention alternatives or exclusions, but the context is clear enough.

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 the full burden. It mentions the underlying command (Get-MtTestInventory) but does not disclose whether the operation is a safe read, any prerequisites, or the return format. This is a notable gap for a tool with no annotation support.

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 only two sentences, with the first sentence front-loading the action and resource and the second providing actionable usage guidance. Every word earns its place, with 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?

For a zero-parameter list tool, the description covers what it lists and how to use the output. It does not describe the response structure or potential caveats, but given the tool's simplicity, it is adequately complete for an agent to select and 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?

The input schema has zero parameters, and schema coverage is 100%, so the baseline is 4. The description adds meaningful context by specifying 'every test tag' and the tool's purpose, which is not captured in 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 clearly states the action ('List'), the resource ('test tags available in the installed test suite'), and the method ('via Get-MtTestInventory'). It also differentiates from sibling tools by noting the tags are used to scope run_maester_tests.

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 explicitly tells the agent to use these tags to scope run_maester_tests, providing clear context for when to use this tool. It does not explicitly mention when not to use it or name alternatives, but the guidance is sufficient for a simple listing 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 must fully disclose behavioral traits. It only states the merge action and the wrapped functions, without mentioning side effects (e.g., whether input files are modified), required permissions, or how the output file is handled. This is a significant gap for a tool that likely creates files.

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 concise sentences: the first clearly states the primary purpose, and the second provides implementation context. There is no filler, and the structure is front-loaded and easy to parse.

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 two-parameter tool with full schema coverage and no output schema, the description is sufficient to convey the core workflow. However, it could be slightly more complete by noting prerequisites (e.g., the results folder must contain valid JSON files) or clarifying that the output HTML file may be overwritten if it already exists.

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 descriptions cover both parameters (resultsFolder and outputHtml) at 100%, so the baseline is 3. The tool description adds minimal extra meaning beyond the schema, though it does relate the parameters to the overall merge workflow. No additional format, default, or validation details are provided.

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 a specific action (merge), the input (per-tenant Maester result files), and the output (single multi-tenant HTML report), distinguishing it from sibling tools that run, update, or retrieve tests. The phrase 'for MSPs / multi-tenant orgs' adds context but is not necessary for purpose clarity.

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 mentions 'for MSPs / multi-tenant orgs' to signal the target audience, but it does not explicitly state when to use this tool versus alternatives or provide exclusions. The usage is implied rather than directly guided, leaving the agent to infer the intended scenario.

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 behavioral disclosure. It states that it simulates a sign-in and returns policy application results, which implies a read-only operation. However, it does not explicitly mention the absence of side effects, required permissions, rate limits, or failure behavior. The description is adequate but not detailed.

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 concise sentences: the first states the action and method, the second states the output. Every sentence adds meaningful information with no redundancy or 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?

Given no annotations and no output schema, the description provides a clear high-level outcome ('Returns which policies apply, block, or grant'). It is sufficient for the tool's apparent simplicity, though it lacks explicit guarantees about non-mutation, auth requirements, or output structure. Overall, it is complete enough for most 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?

Schema description coverage is 100%, so the baseline is 3. The description adds no parameter-specific information beyond what the schema already provides. The parameters (userId, appId, ipAddress, devicePlatform, deviceCompliant) are self-explanatory and do not require additional narrative from the description.

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 specific action (simulate a user sign-in) and the resource (Conditional Access policies), along with the method (Graph evaluate API). It also distinguishes itself from sibling tools by being the only one focused on CA policy simulation rather than Maester tests or security posture.

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 usage is implied: you would use this tool to simulate a sign-in to evaluate Conditional Access policy outcomes. However, there is no explicit guidance on when to use this vs alternatives, nor any exclusions or prerequisites mentioned. It provides a clear functional purpose but lacks explicit usage 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?

With no annotations provided, the description carries full behavioral burden. It discloses the return format (pass/fail summary and file paths) and runtime (2–10 minutes), which is useful context. However, it does not mention potential side effects, permission requirements, or whether the tests are read-only, leaving some behavioral aspects opaque.

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 concise sentences that front-load the purpose, output, scoping mechanism, and runtime. Every clause adds distinct information with no redundancy or filler, making it easy to scan quickly.

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 7 parameters, no required fields, and no output schema, the description covers essential context: what it runs, what it returns, scoping options, and time expectations. It doesn't elaborate on all flags, but the schema covers those. Slightly more context on prerequisites or typical use cases would make it 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 input schema has 100% description coverage for all parameters, so the baseline is 3. The description only summarizes scoping ('Scope with tags and services') without adding meaning beyond what the schema already provides for each parameter like tags, services, useDrift, etc.

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 a specific action ('Run Maester 2.2 security tests') against a defined resource ('Microsoft 365 / Entra tenant'), and mentions the output (pass/fail summary) and execution scoping. It distinguishes itself from sibling tools like get_failed_tests or get_security_posture_summary by focusing on the execution rather than result retrieval.

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 is the tool to execute tests and mentions scoping via tags/services, but it does not explicitly say when to use it over alternatives like run_ca_whatif or audit_ai_agents. There is no direct 'use this when' or 'use X instead' guidance, though the tool's action-oriented nature makes the intended context fairly clear.

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 for behavioral disclosure. It states that it updates files (implying a mutation) and reports a version, but does not disclose potential side effects (e.g., overwriting local changes), required permissions, network access, or reversibility. This is insufficient for a mutation tool with zero annotations.

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, focused sentence that states the action and the result. There is no fluff or redundancy, making it appropriately sized and front-loaded.

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 description covers the main operation and the reported output, but given the absence of annotations and output schema, it does not fully detail side effects, prerequisites, or what 'latest versions' entails. This is a minimal viable description but leaves gaps for a tool that performs a file-modifying update.

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 schema coverage is trivially 100%. According to the rubric, 0 parameters sets a baseline of 4. The description adds no parameter info because there are none to explain.

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 ('Update') with a clear resource ('the Maester module and test files') and states the output ('report the resulting module version'). This clearly distinguishes it from sibling tools like run_maester_tests, which runs tests, and audit_ai_agents, which audits agents.

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 provides no guidance on when to use this tool vs. alternatives. It does not mention prerequisites, exclusions, or alternatives. The only implied usage is that you need to update the Maester module, but there is no explicit context or comparison with siblings.

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