Stigmer

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

With no annotations, the description carries full transparency burden. It discloses the mechanism (calls SimulatePrincipalPolicy), the return format (resolution and evaluation fields), and the credential requirement (without them, evaluation=unknown with reason). This is a substantial disclosure of behavior, though it does not state whether the operation has side effects or mention 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 three sentences, front-loaded with the primary purpose, then mechanism, then requirements/edge case. Every sentence adds value, and there is no fluff or repetition. This is exemplary conciseness.

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 has no output schema and no annotations, the description covers purpose, mechanism, return values (resolution and evaluation), and the credential failure mode. It is reasonably complete for a pre-flight check, though it could elaborate on edge cases like 'unresolved' or error conditions. Overall, it provides enough context for an agent to select and invoke the 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?

Schema description coverage is 100% with detailed descriptions for workflow, operations, and principal_arn. The description adds contextual meaning by explaining that the tool resolves IAM actions and simulates against the current role or given principal, but this largely mirrors schema info. Baseline 3 is appropriate as the schema already provides strong 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 clearly states it is a 'Pre-flight authorization check for an AWS operation', with specifics about resolving IAM actions and using SimulatePrincipalPolicy. It distinguishes itself from siblings like list_workflows and verify by its focus on policy simulation and authorization evaluation.

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 when-to-use context: before an AWS operation to check authorization. It also notes a requirement (AWS credentials) and its failure mode, but does not explicitly mention alternatives or exclusions. This is clear context without explicit alternatives, matching the 'clear context, no exclusions' level.

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 of behavioral disclosure. It implies a read-only operation by saying 'List all methods', but does not explicitly state side effects, error behavior, or access requirements, leaving some transparency 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 a single sentence, front-loaded with the primary action ('List all methods'), and contains no redundant 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?

Given the tool's simplicity (one parameter, no output schema) and the presence of sibling tools, the description sufficiently covers what it does and when to use it. The instruction to use after list_services provides enough context for correct selection.

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 fully describes the 'service' parameter, including its purpose and source ('Get these from list_services first'), and the tool description simply restates this information without adding new meaning. This meets the baseline for high schema coverage.

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 action ('List all methods') and resource (a given library or service), distinguishing it from siblings like list_services which list services themselves. The verb is specific and the scope is well-defined.

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 instructs to use this tool after list_services to 'drill into a specific one', and the schema parameter repeats this guidance ('Get these from list_services first'). This provides clear sequencing and contextualizes the tool relative to an alternative.

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 burden for behavioral disclosure. It states a read-only list operation, which is inherently transparent, but does not describe output format, potential size, or any other side effects. It's adequate but minimal.

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 that front-loads the verb 'List' and immediately provides guidance. Every word earns its place; no filler or redundant phrasing.

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 with no output schema, the description covers the essential purpose and usage. It could include what details are returned per service, but for a discovery tool, this is sufficient and not a critical 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, making schema coverage trivially complete. The description adds no parameter details, but with no params to document, the baseline of 4 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 lists libraries and services with verified method contracts, which is a specific verb+resource. It also distinguishes itself from siblings like list_methods and list_workflows by focusing on the top-level catalog, making it unambiguous.

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?

"Use this first to discover what's available, then query for specific methods" provides an explicit usage context and workflow, though it doesn't name alternative tools directly. It implies this is the entry point before calling other query tools, which 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 burden of disclosing behavior. 'List' implies a non-destructive, read-only operation, but the description does not explicitly state this or provide additional context such as authentication requirements, return format, or side effects. It is minimally transparent but lacks proactive behavioral disclosure.

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 directly conveys the tool's purpose without redundancy. Every word earns its place, and it is appropriately sized for the tool's simplicity.

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 parameters, no annotations, and no output schema, the description is largely sufficient. It explains what is listed and the domain context. However, it could marginally improve by specifying the return format (e.g., an array of workflow names) or explicitly noting the operation is read-only, but these are not critical gaps.

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, which sets a baseline of 4. The description does not need to explain parameter semantics since none exist, and it adds no unnecessary detail.

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 lists 'curated named workflows' for generating least-privilege IAM policies. It uses a specific verb (List) and resource (workflows), and adds scoping detail (curated, named, least-privilege IAM policies) that distinguishes it from sibling tools like list_methods and list_services.

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 for when to use this tool (when needing workflows for IAM policy generation), but it does not explicitly state when not to use it or mention alternatives. The purpose is implied, but no exclusionary guidance is given compared to sibling list 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?

With no annotations provided, the description must disclose behavior on its own. It reveals that the tool 'returns the exact policy with confidence tier and any unresolved operations,' which is useful output context. However, it doesn't explicitly state whether this is a read-only operation or if it makes any AWS changes, leaving ambiguity about side effects. This is a clear 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 composed of two sentences that are direct and informative. The first sentence states the purpose, the second explains inputs and outputs. Every word contributes value, with no fluff or repetition of schema details. This is exemplary conciseness.

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 does a good job of outlining the return content: 'exact policy with confidence tier and any unresolved operations.' It could be more detailed about the exact structure or error cases, but for a relatively simple generation tool, it covers the essential information needed by an 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 already documents all three parameters with 100% coverage, so the baseline is 3. The description adds meaningful semantics by indicating the parameters are alternative input modes ('Pass a named workflow, explicit IAM actions, or a description'), which clarifies that you should provide at least one but not all. This goes beyond the schema's individual descriptions.

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 function: 'Generate a least-privilege IAM policy for an AWS workflow.' It uses a specific verb (generate), specifies the object (IAM policy), and is distinct from sibling tools like list_workflows and query, which perform different functions. This makes the purpose unambiguous.

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 explains that you can provide 'a named workflow, explicit IAM actions, or a description,' which gives clear input options. However, it doesn't explicitly state when to use this tool over alternatives or mention using list_workflows to discover workflow names, so there's room for improvement but the usage context is 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?

No annotations exist, so the description must bear full weight. It reveals the search scope ('any library') and accepts arbitrary text, but doesn't disclose likely read-only behavior, result shape, or how limit/packages affect results. There's no contradiction, but the behavioral profile is under-specified.

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 short sentences, front-loaded with the primary action and then input guidance. No redundant phrasing; every word contributes.

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 5 parameters, no required fields, no output schema, and no annotations, this description leaves many questions open (e.g., what does limit do? how are packages combined? what does a result look like?). The free-text guidance helps but does not provide enough context for a new agent to use all parameters effectively.

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 covers only query and error_type (40%). The description elaborates on the query concept with more example categories. But sig, limit, and packages lack any description or complementary explanation, so the description only partially compensates for the schema gaps.

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?

Description states 'Search for verified method contracts for any library' – a specific verb and resource. It also describes input flexibility (any text), which helps distinguish from list-oriented siblings. However, it doesn't explicitly name alternatives or edge cases, so it's not a 5.

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?

Advises using free-form text and gives examples (library name, method, what you're building, error). This implies broad search usage, but doesn't contrast with list_methods or list_services or indicate when to use structured enumeration instead. No 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?

No annotations are provided, so the description must carry the full behavioral burden. It discloses the three actions but does not mention side effects, persistence, required permissions, return format, or what 'register' actually does to the system. The mutation nature is only implied by the word 'Register.'

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—two sentences with no filler—and leads with the core purpose 'Register a fix,' making it easy to scan and understand.

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 has 9 parameters, no annotations, and no output schema, the description is too sparse. It explains only the action parameter and omits details about other required parameters, return values, or operational behavior, leaving significant gaps for an agent 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?

The schema has 0% description coverage, but the description adds meaning to the 'action' parameter by explaining its enum values. However, it does not address other parameters like library, symbol, env, or error, leaving most of the 9 parameters 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?

The description opens with 'Register a fix,' a clear verb+resource combination, and then enumerates three distinct actions with their meanings. This makes the tool's purpose explicit and differentiates it from sibling read-only tools like list_methods and query.

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 provides explicit context for when to use each action: 'confirm (it worked)', 'append_thread (variant worked)', 'new_receipt (nothing matched, I fixed it)'. This is clear action-level guidance, though it does not directly compare against sibling tools or state when not to use the tool overall.

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 discloses the underlying AWS engine (SimulateCustomPolicy), the exact output structure, the behavior when credentials are missing (verified=unknown with reason), and the preprocessing of wildcarded operations. This is substantial behavioral transparency beyond minimal expectations.

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 three sentences long, front-loaded with the core purpose, followed by output format and prerequisites. Every sentence contributes meaningful information without redundancy or fluff.

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 lack of an output schema, the description adequately explains the return values (verified, grants_all, grants_extra) and the credential prerequisite, including the fallback behavior. It does not precisely define what grants_all and grants_extra signify, but the context is sufficient for an agent to understand the tool's basic usage and interpretation.

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 description is not required to repeat parameter definitions. It adds some context by explaining that 'operations' are intended IAM actions and that wildcards are expanded, but it does not elaborate on the 'workflow' parameter beyond what the schema already states, keeping the added value at baseline.

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: verifying a generated policy against intended operations using AWS's SimulateCustomPolicy engine. It specifies a concrete action and resource, and distinguishes itself from siblings like 'policy' which generates policies.

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 after policy generation ('Feed a generated policy back') and identifies a key prerequisite (AWS credentials). However, it does not explicitly mention when to avoid using this tool or name alternative verification approaches, so guidance is clear but not exhaustive.

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