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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds context by noting 'token-optimized responses' and specifying that the return is a dictionary with a list of groups and pagination metadata, going beyond the annotation baseline.

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 front-loaded with its primary purpose and then uses a compact Args/Returns list. Every sentence contributes information, and there is no filler or redundant repetition of schema fields without added value.

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?

This is a straightforward retrieval operation with an output schema and clear annotations. The description covers all parameters, pagination behavior, and the return shape, so an agent has everything needed to call it correctly without further research.

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 fully compensates. The Args section explains every schema parameter: domain enum values, remove_revoked_deprecated semantics, limit's default and purpose, and offset's pagination role, adding far more meaning than 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 opens with 'Get groups from the MITRE ATT&CK framework', specifying a precise verb and resource. The word 'groups' distinguishes it from sibling tools like get_techniques and get_tactics, and the added 'token-optimized responses' further clarifies its purpose.

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 tool is for retrieving ATT&CK groups but never explicitly contrasts it with sibling tools or states when not to use it. There is no alternative routing such as 'for techniques, see get_techniques', so usage guidance is left 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds value by explaining pagination metadata, token-optimized responses, and the remove_revoked_deprecated behavior, which goes beyond the 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 well-structured with a concise summary followed by clearly labeled Args and Returns sections. It front-loads the core purpose and avoids unnecessary fluff, though a slightly tighter format would be even better.

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?

All four parameters are explained, the return shape is described, and an output schema exists, so the agent has enough to call the tool correctly. The only notable gap is the absence of guidance distinguishing this from related mitigation-specific sibling tools.

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%, but the description compensates by explaining every parameter: domain values, remove_revoked_deprecated meaning, limit, and offset for pagination. However, it states a default of 20 for limit while the schema default is null, creating a minor inconsistency.

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 verb and resource: 'Get mitigations from the MITRE ATT&CK framework'. It is unmistakably distinct from sibling tools like get_techniques, get_tactics, and get_groups, which target different entities. The 'token-optimized responses' hint adds a useful precision cue.

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 obvious that this tool is for retrieving mitigation objects, but it offers no explicit guidance on when to choose this over the more specific sibling get_techniques_mitigated_by_mitigation. Usage context is implied rather than stated.

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 establish read-only, idempotent, and non-destructive behavior. The description adds useful context by promising token-optimized responses and clarifying that the result is a dictionary with a software list plus pagination metadata, which goes beyond the structured 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 well organized with a front-loaded purpose statement followed by Args and Returns sections. It is slightly redundant with the schema, particularly for domain enums and parameter names, but every section adds some operational value.

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 all parameters, the return shape, pagination, and domain options, and an output schema exists, so completeness is strong. The main gaps are the lack of explicit alternative routing and the minor default inconsistency for limit.

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?

With 0% schema description coverage, the description carries the full burden and does provide a meaningful line for each parameter, including defaults and an example for software_types. It is strong, but the stated limit default of 20 conflicts with the schema's null default, preventing a perfect score.

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 retrieves software from the MITRE ATT&CK framework, with additional detail on filtering and pagination. It is easily distinguished from sibling tools like get_techniques and get_tactics because each targets a distinct ATT&CK resource type.

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 its use case by naming the resource type and listing parameters, so an agent can infer when to call it. However, it does not explicitly state when to prefer this tool over alternatives or mention situations where another sibling would be more appropriate.

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=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds some context by mentioning token-optimized responses and pagination metadata, but it does not elaborate on how token optimization works or what pagination metadata is returned. This is acceptable but leaves room for more transparency.

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 well-structured with a clear one-line summary, a compact Args block, and a Returns line. It avoids fluff and front-loads the purpose. The inclusion of ctx as an argument that is not in the schema is slightly extraneous but quickly clarified as injected by the server.

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-retrieval tool with an output schema and rich annotations, the description covers the essential information: purpose, parameters, and return shape. It does not mention how to choose this tool over siblings, but given the simplicity and output schema, it is largely complete. The limit default inconsistency is the main 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 schema has 0% description coverage, but the description's Args section compensates by explaining domain, remove_revoked_deprecated, limit, and offset. It adds meaning beyond the schema (e.g., what 'remove revoked or deprecated' does, what 'offset' is for). However, there is a discrepancy: the description says the limit default is 20, while the schema states default null, which could confuse an agent.

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 ('Get tactics') and a clear resource ('MITRE ATT&CK framework'), which is unambiguous. However, it does not explicitly distinguish itself from sibling tools like get_techniques or get_techniques_by_tactic, though the resource name is inherently informative.

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 explicit guidance on when to use this tool versus its siblings. There is no mention of alternatives, exclusions, or preferred use cases beyond stating that it retrieves tactics. The sibling tool names are visible in context but not referenced in the description itself.

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=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds no behavioral context beyond a generic 'Returns: Dictionary', offering no guidance on not-found behavior, error handling, or domain-specific effects.

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 first sentence is clear and front-loaded, but the docstring includes boilerplate about the injected ctx and a redundant 'Returns: Dictionary containing the technique' line that overlaps with the output schema. It is not bloated, yet not 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 simple read-only fetch by ID, the description covers both parameters, the domain choice, and the return shape. With an output schema present and readOnly/idempotent annotations, nothing needed to invoke the tool correctly is missing.

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, and it does: it explains technique_id with a concrete example ('T1055') and lists the three valid domain values. This adds real meaning beyond the bare schema properties, though it does not elaborate on format edge cases.

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 an exact verb ('Get'), the resource ('technique'), and the key selector ('MITRE ATT&CK ID'), e.g., 'T1055'. This clearly distinguishes it from sibling tools like get_techniques or get_techniques_by_tactic without needing to open the schema.

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 appropriate use case—call this when you already have a specific MITRE ATT&CK ID—but it never explicitly names alternatives or states when not to use it. No exclusions or comparison to sibling tools are provided.

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 establish readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds useful behavioral context beyond that: responses are token-optimized, including descriptions consumes more tokens, and the return value contains pagination metadata. There is no contradiction with the 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 lead sentence is concise and the parameter bullets are compact and informative. It is longer than strictly necessary, and 'token-optimized responses' is somewhat vague, but each line earns its place by explaining a parameter or the return shape.

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 6 parameters, annotations, and output schema, the description covers the invocation essentials: all arguments are explained, pagination is described, and the return is summarized. The main missing piece is explicit routing among the sibling tools, but that gap is also captured in usage_guidelines.

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?

With 0% schema description coverage, the description carries the whole burden and succeeds by explaining every parameter—domain values, default 20 limit, offset pagination, subtechnique inclusion, revoked/deprecated filtering, and the token cost of descriptions. This adds meaning beyond the bare names, types, and defaults 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 names a specific operation and resource: it retrieves techniques from the MITRE ATT&CK framework, and the parameter list clarifies scope by domain and subtechniques. However, it never states whether this is the unfiltered/general listing as opposed to the filtered sibling tools such as get_techniques_by_tactic, get_techniques_used_by_group, or get_technique_by_id, so it is clear but not fully differentiating.

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 a general technique-fetching tool through its broad name and pagination/filtering parameters, but it gives no explicit when-to-use or when-not-to-use guidance and does not mention any sibling tools. An agent has to infer that get_techniques_by_tactic or get_technique_by_id would be better choices for narrower lookups.

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 communicate safe, idempotent, read-only behavior, so the description does not need to restate that. It adds useful context about pagination metadata and the default limit of 20, but does not go deeper into edge-case behavior like handling an unknown tactic shortname or empty results.

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 compact, well-organized docstring with Args and Returns sections. Each parameter gets a short, meaningful explanation, there is no filler, and the core purpose is front-loaded in the first sentence.

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 moderate complexity and the presence of an output schema, the description provides everything needed to invoke it correctly: all parameter semantics, the domain choices, pagination behavior, and the return shape. No critical invocation detail appears to be missing.

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 carries the full burden of explaining all five parameters. It successfully does so: tactic_shortname is given example syntax, domain lists allowed values, remove_revoked_deprecated is explained, and limit/offset are defined as pagination controls with the default limit noted.

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 opening phrase 'Get techniques by tactic' names a specific verb, resource, and filtering dimension, and the parameter descriptions clarify exactly what tactic and domain mean. This cleanly distinguishes it from siblings like get_techniques, which returns techniques without a tactic filter, and get_technique_by_id, which targets a single technique.

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?

Usage is implied by the name and description: use it when you want techniques filtered by a tactic shortname. However, it never explicitly contrasts with sibling tools like get_techniques or get_techniques_used_by_group, so an agent is left to infer when this tool is the right choice over alternatives.

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=true, idempotentHint=true, and destructiveHint=false, so the description does not need to repeat those. It adds return-type context ('Dictionary containing the mitigation, a list of techniques and pagination metadata') and mentions pagination in the Args, which is useful. However, it doesn't disclose any additional behavioral traits such as rate limits, authentication, or what happens when no techniques are found.

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 opens with a crisp one-liner, then a structured Args list and Returns note. It is reasonably compact and well-organized. The Args section is at times tautological (e.g., 'mitigation_name: The name of the mitigation') but not excessively verbose, and the most important info is 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?

Given the tool has 4 parameters, one required, an output schema, and safety annotations, the description covers the return format and pagination. However, it omits usage guidelines (when to choose this tool over siblings) and lacks any example or edge-case behavior. For a read-only query tool, it is adequate but not 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 schema has no parameter descriptions (coverage 0%), so the description must compensate. It provides some meaning for 'limit' and 'offset' (pagination semantics) and restates the enum values for 'domain', though the schema already lists them. 'mitigation_name' is merely described as 'The name of the mitigation,' adding little beyond the parameter name. Overall, partial compensation but could be more descriptive.

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 'Get techniques mitigated by a mitigation,' which is a clear verb-resource pair and distinguishes this tool from siblings like get_techniques (all techniques) and get_techniques_by_tactic (by tactic). It is specific but doesn't explicitly contrast with alternatives; the title and one-liner are unambiguous enough.

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 guidance on when to use this tool versus its siblings. The description does not mention prerequisites, filters, or scenarios where a different tool would be more appropriate. An agent must infer the use case from the name alone.

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=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds mildly useful behavioral context by stating the return shape (group, list of techniques, pagination metadata) and describing pagination via limit/offset. It does not go deeper into edge cases such as unknown group names or empty results, but that gap is minor given the 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 well-organized docstring with an opening summary followed by concise Args and Returns sections. Every parameter earns its place and there is no redundant prose. The formatting is slightly heavier than necessary, but it remains readable and 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 read-only lookup tool, the description covers the essential invocation details: required group_name, optional domain, and pagination controls. The output schema and annotations take care of return structure and safety behaviorgrave. The only material omission is usage guidance relative to sibling tools, which is handled by the tool name but not described explicitly.

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 0% description coverage, and the description compensates by explaining each parameter: group_name as the group to query, domain with its allowed values, limit as the maximum number of techniques, and offset as the pagination starting index. This adds meaning that is absent from the schema's bare properties. It could be improved by noting expected types, but the schema already provides types and defaults.

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 starts with a clear verb and resource: 'Get techniques used by a group.' This directly distinguishes the tool from siblings like get_techniques and get_techniques_by_tactic by specifying the grouping dimension. The title reinforces the purpose without ambiguity.

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: use this tool when you need techniques associated with a specific group. However, it provides no explicit guidance on when not to use it or when to prefer a sibling tool such as get_techniques_by_tactic or get_techniques. The description defines what the tool does but does not give selection criteria.

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