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

With no annotations, the description carries the full burden. It explicitly states the tool is non-destructive, which is a key behavioral trait. However, it does not disclose other aspects such as performance, rate limits, or what happens if the limit parameter is omitted.

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, efficient sentence with no wasted words. It front-loads the key verb and resource, then enumerates the payload components succinctly.

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 output schema and no annotations, the description provides a reasonable overview but lacks details on return format, pagination, or how the limit parameter interacts with the payload. It is adequate for a simple tool but not fully comprehensive.

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 description does not explain the 'limit' parameter at all, despite 0% schema coverage. While it lists components of the payload, it fails to clarify how the parameter affects the output, leaving the agent to infer its purpose.

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 generates a non-destructive audit payload encompassing config, session, report, candidates, dry-run metrics, and safety metadata. It uses a specific verb ('Generate') and resource ('audit payload'), and distinguishes from sibling tools that focus on individual aspects like cleanup or discovery.

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 versus alternatives, nor any context on prerequisites or exclusions. It simply states what the tool does without answering 'when' or 'why not'.

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 must carry behavioral info. It explicitly states 'without terminating anything,' indicating a safe, read-only operation. However, it omits details on output, permissions, or side effects beyond 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, well-front-loaded sentence with no superfluous words. It efficiently conveys the core behavior.

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?

Despite low complexity (2 params, no output schema), the description lacks parameter explanations and output description. It is insufficient for an agent to fully understand tool behavior, especially given the sibling context.

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 explain parameters. It does not mention 'min_age_minutes' or 'include_command_line' at all, leaving their purpose entirely undocumented.

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 plans an auto-cleanup dry run without termination, including the nuance 'even when auto-cleanup is disabled.' However, it does not distinguish from the sibling tool 'managed_cleanup_dryrun', which likely has a similar 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?

No guidance on when to use this tool versus alternatives like 'managed_cleanup_dryrun' or real cleanup tools. The only hint is 'even when auto-cleanup is disabled,' implying it works regardless of that setting, but no explicit usage context or 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?

Without annotations, the description carries the full burden. It discloses one behavioral fact: 'Auto-cleanup is disabled by default.' However, it does not mention if the tool is read-only, what 'gates' refer to, or any side effects, leaving gaps in 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 extremely concise: two sentences with no wasted words. Every sentence adds value, stating the purpose and a key behavioral fact.

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 parameters, no output schema, and no annotations, the description is minimally adequate. It explains what the tool shows and a default state, but lacks detail on return format or what 'gates' entails, leaving room for improvement.

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 0 parameters, and schema coverage is 100% (since no parameters exist). Per guidelines, baseline for 0 parameters is 4. The description adds no parameter details, but none are needed.

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: 'Show experimental auto-cleanup policy status and gates.' It uses a specific verb ('Show') and resource ('policy status and gates'), distinguishing it from sibling tools like auto_cleanup_dryrun or managed_cleanup_dryrun which perform actions rather than display status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like auto_cleanup_dryrun or managed_cleanup_dryrun. The description only states what the tool does without offering context on optimal use cases or when to avoid 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?

No annotations exist, so the description carries full burden. It discloses the key behavior of not exposing command line secrets, which is positive. However, it does not state whether the tool is read-only, has side effects, or requires specific permissions.

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 of 17 words, concisely conveying the tool's purpose and a key behavioral constraint. No redundant or extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and zero parameters, the description covers the essential aspects: what is explained (config, paths, directory, defaults) and a notable behavioral trait (no secrets). It does not describe output format, but completeness is high for a simple explain 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?

The tool has zero parameters and schema coverage is 100%. Baseline score of 4 applies because the description adds context about what the tool explains, which is effectively the input.

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 explains effective config, config paths, data directory, and safety defaults. The verb 'Explain' and resource 'config' are specific, but it does not explicitly differentiate from sibling explain tools like policy_explain or process_explain.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No usage guidelines are provided. The description does not mention when to use this tool vs alternatives, nor any prerequisites or exclusions. The agent must infer from the sibling names.

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?

Emphasizes non-destructive nature, not scanning or terminating, fully disclosing safety despite no 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?

Two sentences, front-loaded with action, no waste.

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?

Complete for a simple tool with one optional param; no output schema needed.

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 coverage is 100%, so baseline 3. Description does not add meaning to the parameter.

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 clearly states it returns guidance about when to use clean-process-ended, which is a specific verb+resource. It distinguishes from sibling tools that perform actual process actions.

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?

Implies using this tool when needing guidance on clean-process-ended, but lacks explicit alternatives or when-not cases.

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 should disclose behavioral traits. It implies a non-destructive read but lacks details on permissions, side effects, rate limits, or data freshness.

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 and front-loaded, but it omits crucial details about parameters and output, making it less effective despite being concise.

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 output schema and one parameter, the description should explain what the returned data includes and how the optional parameter affects it. It does not.

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 sole parameter 'include_recent_events' (boolean) is not mentioned in the description. With 0% schema coverage, the description provides no additional 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 clearly states the verb 'Read' and identifies three specific resources (ledger summary, snapshot metadata, cleanup events), distinguishing it from sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives, nor any exclusions or prerequisites.

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 provided, but the description clearly states the tool is dry-run only and never terminates processes, which is a key behavioral trait. It lacks mention of any logging or state changes, but for a zero-parameter tool, this is sufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loading purpose and constraint. 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?

Given no parameters and no output schema, the description covers purpose and scope well. It could optionally describe the return value (e.g., a plan list), but is functionally 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?

No parameters exist, so the description need not add parameter info. Schema coverage is 100%, and baseline 4 applies for zero-parameter tools.

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: planning cleanup for managed processes. It emphasizes 'dry-run only' and 'never terminates processes,' distinguishing it from execution tools like process_cleanup.

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 use for managed processes only, but does not explicitly state when to use this over siblings like auto_cleanup_dryrun. No alternatives or exclusions are mentioned.

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 should disclose behavioral traits like idempotency, authorization needs, or side effects. It only states it produces a report, but does not indicate if it is read-only, requires privileges, or has any impact.

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?

Single concise sentence that front-loads the action and lists key states. No redundant or irrelevant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and zero parameters, the description is minimal. It does not specify the return format, whether the report is a summary or detailed list, or how to interpret results, leaving some gaps for a complete understanding.

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?

Tool has zero parameters, so the description does not need to add parameter details. Per guidelines, baseline is 4. Description adequately covers the tool's function without needing parameter explanations.

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 specifies the tool reports lifecycle state for cpe-run managed processes and lists five specific possible states (running, missing, exited, expired, PID-reuse mismatch), making the purpose clear and distinct from sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus sibling tools like managed_stale_report or process_explain. The description does not mention appropriate contexts, alternatives, or 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?

With no annotations, description carries full burden. Only discloses it never terminates, but omits behavior like return format, error handling, or required permissions.

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, no filler. Could be slightly more structured but efficient overall.

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 tool with one parameter and no output schema, description is adequate but missing crucial context like what the 'explanation' contains or example usage.

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 coverage is 0%, so description must compensate. It mentions 'managedProcessId' but adds no details on format, constraints, or examples beyond 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?

Description states 'Explain one cpe-run managed process record by managedProcessId', which is specific verb+resource. It distinguishes from sibling 'process_explain' by targeting managed processes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives like 'managed_process_list' or 'process_explain'. The note 'never terminates' is behavioral but not 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, description must disclose behavioral traits. It states 'report-only' implying no destructive actions. However, it does not mention pagination, performance implications, or access requirements. Minimal but acceptable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no redundant information. Front-loaded with the core action and scope. Every word is useful.

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 tool with one optional parameter and no output schema, the description is mostly adequate except for missing parameter documentation. It covers the basic purpose and read-only nature.

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 'include_exited' has no description in the schema (0% coverage). The description does not explain what this boolean does, leaving the agent unaware of its effect on the output.

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?

Clearly states it lists processes launched through cpe-run lifecycle management. The phrase 'report-only' indicates read-only nature. However, it does not differentiate from sibling tools like managed_lifecycle_report or managed_process_explain.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. Sibling tools exist for similar purposes (e.g., managed_lifecycle_report, managed_process_explain) but no comparison or exclusions 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?

With no annotations, the description carries full burden for behavioral disclosure. It only states 'never terminates processes' but fails to clarify if the reconcile operation is read-only or mutates records, what side effects occur, or if it requires special permissions.

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, efficient sentences with no redundancy. The key information 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?

Despite no output schema and no annotations, the description is too minimal. It does not explain what 'reconcile' entails, whether it modifies data, or what the output looks like, leaving an agent underinformed for a potentially complex action.

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?

There are zero parameters, so according to rules the baseline is 4. The description adds no parameter information, but no parameters exist to document.

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 verb 'reconcile' and the specific resource 'explicit cpe-run managed process records' against the current process table. It distinguishes itself from siblings by explicitly noting it never terminates processes.

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 that this tool does not terminate processes, which is a key usage guideline. However, it does not explicitly state when to use this tool versus alternatives like 'process_cleanup' or 'managed_cleanup_dryrun'.

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 must fully disclose behavior. It states 'report-only evidence' which indicates non-destructive action, but does not explain what 'stale' means, the format or destination of the report, or any side effects beyond being read-only.

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?

Extremely concise with two sentences. The first sentence clearly states purpose, and the second adds behavioral note. 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?

For a tool with no parameters and no output schema, the description is minimal. It does not explain what constitutes 'stale', how results are returned, or how it differs from sibling reporting tools. More context would be helpful for 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?

No parameters exist, so baseline score of 4 applies. Description adds no parameter info because none are needed.

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?

Clearly states the tool reports stale managed process records. The verb 'report' and resource are specific. However, it does not explicitly differentiate from similar sibling report tools like stale_session_report or managed_lifecycle_report.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives or when not to use it. The description only says it is report-only, implying safe usage but lacking 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?

Without annotations, the description must disclose behavioral traits. It adds a key safety note ('never terminates processes'), but does not mention other aspects like idempotency, side effects, or performance. This is 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?

Two sentences, front-loaded with the main purpose, no wasted words. Efficient and 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?

Given no output schema and minimal param details, the description is insufficient. It does not explain what the policy gates explanation includes (e.g., active rules, conditions), leaving the agent with a vague understanding of the output.

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 needed to explain parameter meaning. It only mentions pid implicitly via 'for one PID' but does not describe include_command_line at all. No added meaning beyond schema types.

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 clearly states the tool explains cleanup and auto-cleanup policy gates for a single PID, distinguishing it from sibling tools like process_explain (general process info) and auto_cleanup_dryrun (simulation). Verb + resource is specific and 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 lacks explicit guidance on when to use this tool versus alternatives. It implies usage for policy understanding before cleanup actions, but no direct context or exclusions 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?

With no annotations, the description carries full burden. It discloses that dry_run=true is the intended mode, that real cleanup is disabled (dry_run=false blocked), and includes safety gate context. It does not discuss return values or error states, but the core behavioral trait (dry-run) is 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?

Two sentences, no redundancy. The first sentence front-loads the primary purpose, and the second delivers critical usage constraints. Every word 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 10-parameter tool with no output schema and no annotations, the description covers the essential behavioral constraint (dry-run only) but omits return format and error handling. 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?

Schema coverage is 50% (5/10 parameters described). The description does not add parameter-level guidance beyond what's in the schema, missing opportunities to explain usage nuances for parameters like confirm_token or scope. Baseline of 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 performs a dry-run on owned_current_session candidates, using a specific verb ('Dry-run') and resource. It distinguishes from siblings like auto_cleanup_dryrun by specifying the scope 'owned_current_session'.

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?

Provides explicit guidance that agents must not call dry_run=false autonomously and explains that real termination is non-operable due to blocked safety gates. However, it lacks comparison to sibling cleanup tools for alternative selection.

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. It clearly states the tool is read-only and non-destructive ('never terminates processes'). This provides strong transparency about its behavior, though it could mention return format or pagination.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no wasted words, front-loaded with key information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is too brief given 5 parameters, no output schema, and no annotations. It does not explain 'grouped by ownership', what 'candidates' are, or any parameter defaults or usage.

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 only 20%, and the description does not explain any parameters. It only describes the overall purpose. For a tool with 5 parameters, this is insufficient.

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 verb 'Return', the resource 'detailed candidates grouped by ownership', and the key constraint 'audit-only and never terminates processes'. This distinguishes it from sibling tools like process_cleanup which likely terminate processes.

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 use for review without side effects by stating 'audit-only and never terminates processes', but does not explicitly state when to use it over alternatives or provide exclusions. Sibling tools like process_cleanup exist, but no guidance is 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 provided, the description carries full responsibility. It ensures the tool is non-destructive by stating it never terminates processes, which is a key behavioral trait. However, it does not disclose other aspects like required permissions, rate limits, or side effects, 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 extremely concise at two sentences, front-loading the primary purpose and adding a critical behavioral note in the second sentence. Every word serves a purpose 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 simple read-only explain tool with no output schema, the description covers the purpose, included evidence, and safety guarantee. However, the omission of parameter details and any context about permissions or output format leaves it somewhat incomplete, especially given the absence of annotations.

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%, and the description fails to mention either parameter (pid or include_command_line). It does not explain that pid is required or what include_command_line controls, forcing the agent to rely solely on the schema, which lacks 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 explains a single PID with ownership evidence, host/tool profiles, reasons, blockers, and cleanup eligibility. It also explicitly distinguishes from siblings by stating 'It never terminates processes,' differentiating it from cleanup tools like process_cleanup.

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 getting an explanation of a process, but it does not provide explicit guidance on when to use this tool versus alternatives like managed_process_explain or process_cleanup_candidates. There are no when-not-to-use instructions or context for preference among siblings.

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?

The description discloses that the tool is read-only (no termination), but with no annotations, it omits potential performance impacts, permission requirements, or details about the reconciliation process. This is adequate but not thorough.

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, dense sentence that front-loads the main actions and ends with a key qualifier. Every word is necessary 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?

The description lacks output schema details, potential resource warnings, and safety info (since annotations are absent). It covers the core purpose but leaves gaps for a moderately complex 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 coverage is 100%, with each parameter already having clear descriptions. The tool's description adds no extra meaning beyond the schema, fitting the baseline of 3.

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 actions: scanning local processes, reconciling with a session ledger, and reporting ownership, with an explicit differentiator 'without terminating anything' that distinguishes it from sibling cleanup tools.

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 phrase 'without terminating anything' implicitly guides the agent to use this for read-only reporting rather than cleanup, but fails to explicitly state when to use this tool vs alternatives like process_cleanup or process_explain.

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 provided, so the description must disclose all behavioral traits. It only states it 'lists', implying a read operation, but lacks any mention of permissions, side effects, rate limits, or what happens if profiles are not configured.

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?

Single, clear sentence with no redundant words. It is appropriately sized but could benefit from a slight structure (e.g., separating purpose from context).

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 explains the purpose (listing profiles) and their use (weak signals for process classification), which provides context. However, it does not describe the output format or any additional details like whether profiles are local or remote, making it only moderately 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 tool has zero parameters and 100% schema coverage, so the description adds no parameter details. Baseline of 4 is appropriate as there is nothing missing parameter-wise.

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 clearly specifies the verb 'list' and the resource 'configured host and tool profiles used as weak signals for process classification', distinguishing it from sibling list tools like managed_process_list which likely list process classifications themselves.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives, nor any conditions or exclusions. The description is purely functional without contextual usage advice.

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 provided; description only says 'summarize', implying read-only but doesn't confirm side effects, permissions, or response format. Insufficient disclosure for a tool with no 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?

Single sentence is efficient but lacks structure. Could be improved with separate sections for parameters and behavior.

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 zero annotations, no output schema, and 2 undocumented params, description should provide more context on 'report partitions', 'top blockers', and 'impact metrics'. As is, incomplete for agent decision-making.

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 has 2 parameters with 0% description coverage; description does not explain min_age_minutes or limit, leaving their meaning entirely to the schema names.

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 clearly states 'Summarize CPU/RSS impact, top blockers, and report partitions for related processes'. It specifies a verb and a distinct resource set but doesn't differentiate from siblings like process_scope_report or process_explain.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. Lacks context or conditions for invocation.

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 bears the full burden. It explicitly states the tool is non-destructive, dry-run, and never returns a confirm token or terminates processes. This adds behavioral context beyond the schema, though it omits details like return format or error handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the main purpose, and every sentence adds value. No superfluous content.

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 zero required parameters and a simple scope, the description covers the essential behavior (non-destructive, dry-run, no confirm token). However, it lacks return value details and examples, which would be helpful for completeness.

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 coverage is 100%, so baseline is 3. The description adds no additional meaning for the 'limit' or 'project_key' parameters 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 clearly states the action ('run a compact non-destructive close-task check') and resource context. It differentiates from sibling tools by emphasizing it's a non-destructive dry-run check that never returns a live confirm token or terminates processes.

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 safe checks but does not explicitly state when to use this tool vs alternatives like auto_cleanup_dryrun or managed_cleanup_dryrun. No when-not or alternative guidance is 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?

No annotations exist, so the description carries the full burden. It states what is shown (read-like behavior) but does not explicitly declare it as read-only, safe, or free of side effects. The verb 'Show' implies no mutation, but explicit disclosure would improve 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?

One sentence lists all relevant outputs without wasted words. The most important information 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?

For a zero-parameter status tool, the description lists four specific pieces of output, which is adequate. However, it does not define terms like 'baseline' or 'epoch', which might be unfamiliar to new users.

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?

There are zero parameters, so the schema provides full coverage. The description does not need to add parameter details, and it implicitly confirms no inputs are required.

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 verb 'Show' is specific, and the resource includes four distinct aspects: MCP instance identity, session epoch, baseline, and watcher status. This clearly distinguishes it from siblings like 'watcher_status' which only covers watcher status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives such as 'watcher_status' or 'session_close_check'. It does not mention prerequisites, exclusions, or 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?

The description explicitly states it is 'report-only', implying no destructive side effects. However, with no annotations, it does not disclose other behaviors like permissions needed, definition of 'stale', or performance implications.

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 and concise. Minor improvement possible by adding a brief note on return format, but it wastes no 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 no output schema, the description should clarify what the report contains or how it is returned. It does not define 'stale' or mention output format, leaving the agent uncertain about results.

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?

There are no parameters, and schema coverage is 100%, so the baseline is 3. The description adds no parameter information, which is fine since there are none.

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 reports stale sessions and is report-only. It specifies the verb 'report' and resource 'previous sessions', but does not differentiate from sibling tools like 'managed_stale_report', leaving some 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?

No guidance is provided on when to use this tool vs alternatives (e.g., 'managed_stale_report', 'session_status'). The description does not indicate prerequisites or context for use.

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?

Despite no annotations, the description explicitly states 'updates the ledger' (a mutation) and 'does not terminate anything' (non-destructive). This provides behavioral clarity beyond the tool name. However, it omits details like rate limits, error behavior, or required permissions.

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, very concise and front-loaded. However, it could include more detail without sacrificing brevity.

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 output schema, optional parameters, and no annotations, the description sufficiently covers core purpose and safety (non-destructive). However, it lacks parameter explanations and usage context, making it incomplete for optimal agent decision-making.

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%; the description does not mention either parameter ('min_age_minutes' or 'limit'). Their purpose and effect remain entirely unexplained, leaving the agent unable to select appropriate values.

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 ('force'), the resource ('watcher reconciliation snapshot'), and timing ('now'). It is specific and distinguishes the tool from siblings like 'watcher_status', but does not elaborate on what 'reconciliation snapshot' entails.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternative tools (e.g., 'managed_reconcile', 'auto_cleanup_dryrun'). It does not specify prerequisites or exclusions, leaving the agent to infer 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?

Describes the watcher as taking non-destructive snapshots and embedded, but lacks details on output format or what 'status' includes. No annotations provided to supplement.

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?

Single sentence, front-loaded, no unnecessary words. Efficient and 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 tool with no parameters and no output schema, the description covers the essential context (what it does, its role). Minor gap: doesn't specify what status fields are 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?

No parameters, so description adds value by explaining tool purpose. Baseline for 0 params is 4, and description is adequate.

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 verb 'show' and the resource 'status of the embedded watcher', and provides context about periodic non-destructive snapshots. It distinguishes from sibling tools like watcher_reconcile_now.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives (e.g., session_status, auto_cleanup_status). Implied for checking watcher status but lacks comparison.

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