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

With no annotations at all, the description carries the full burden and does substantial work: it declares the report is frozen (immutable snapshot), enumerates the semantic guarantees (raw vs canonical status, validation states, error class, caveats), and explicitly states timeouts are never reported as infeasibility. Missing auth/permission requirements and behavior on an unknown run_id keeps it from a 5.

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?

Front-loaded with the verb and resource, then the payload and the id formats. The middle clause is a dense comma-list of return fields, which is information-rich but reads as a run-on; it could be trimmed given an output schema already exists.

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 single-parameter read tool with an output schema, the description covers the input format thoroughly and adds semantic guarantees. The enumerated return fields overlap with what the output schema presumably declares, and invalid-run_id behavior is unstated, but nothing essential for a correct call 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 coverage is 0% (run_id has no description), so the description must compensate, and it does: three run_id shapes are given with concrete examples ('<experiment>/<record>', 'ND-SEED-<seed>', 'MOCK-*'). This is more than the schema provides and enough to construct a valid argument.

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?

States a specific verb and resource ("Read a frozen experiment/run report") and the word "frozen" implicitly separates it from live-status siblings like get_plan_status. It does not name a sibling explicitly, so an agent must infer the boundary rather than being told.

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 "read a frozen report" and the enumerated run_id forms, but there is no explicit statement of when to prefer this over get_plan_status, list_tasks or get_task_info. The agent gets context but no exclusions or routing rule.

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 behavioral burden and does unusually well: it discloses persistence across service restarts and that unverifiable outcomes surface as UNKNOWN rather than being silently converted. It omits whether the call blocks, whether polling is expected, and cost/latency, which matter for a status-query tool.

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?

Front-loaded with verb, resource, and the three query dimensions, and every clause earns its place — the COMPLETED clarification prevents a real misinterpretation. The dense parenthetical enum lists make it slightly heavy to parse but are not wasteful.

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

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

For a one-parameter status reader with an output schema, this is nearly sufficient: status semantics, persistence, and UNKNOWN handling are all covered. The remaining gap is operational — whether an agent should poll and how quickly a run transitions — which is left implicit.

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 the description must compensate for the single run_id parameter; it does add provenance (obtained from start_motion_plan) but not format or validation rules. Much of the semantic detail it provides is about return-value enums, which the output schema already covers.

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?

States a specific verb (Query) and resource (a planning run keyed by run_id) and names the sibling that produces the id (start_motion_plan), which immediately separates it from list_tasks and get_task_info. It also enumerates the three result dimensions, so an agent knows exactly what it will learn.

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 reference to 'run_id from start_motion_plan' establishes the calling context: use this after starting a plan. It gives no explicit exclusions (e.g., when to use list_tasks or get_task_info instead) and no polling guidance, so it stops short of full when/when-not guidance.

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

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

With no annotations, the description does real work: 'Read' signals a non-mutating operation, 'verbatim from config' tells the agent values are raw/non-normalized, and 'data completeness' warns that returned fields may be partial. It omits error behavior for an unknown or malformed task_id, which is the main remaining gap for a tool with zero annotation coverage.

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 tight sentences, zero filler: the payload enumeration comes first and the id-format guidance second. Every clause carries information an agent cannot get from the schema alone.

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?

An output schema exists, so return-value shape need not be explained, and the description still adds the notable caveat that completeness is reported. What's missing is failure behavior for bad task ids and whether config is static or live — modest gaps for a single-parameter read 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 0% and the single task_id param has no schema description, so the description carries the full burden — and it does, spelling out three accepted id forms ('ND-SEED-<seed>', frozen research ids like 'T1_CM2B', and 'MOCK-*' fixtures). It does not say how invalid ids fail or whether these forms are exhaustive.

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?

Opens with a specific verb+resource ('Read one task's configuration') and then enumerates exactly what that configuration contains: workpieces, placement/allocation, robots, planner methods, collision-semantics flags, and data sources. The 'one task' framing implicitly separates it from list_tasks, but no sibling is named explicitly, so it stops short of full differentiation.

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 enumerated payload — an agent can infer this is the tool to reach for when it needs the full config of a single task. However, there is no explicit when-to-use vs. when-to-use-something-else guidance (e.g. versus list_tasks or get_experiment_report), nor any stated preconditions.

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 usefully discloses that sources are read-only and that no task ids are invented, which adds behavioral context beyond the schema. However, without annotations it does not cover ordering, pagination, permission requirements, or how include_mock affects 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?

Two tightly written sentences with the core scope front-loaded and no redundant filler. The parenthetical source list earns its place by defining what counts as a task.

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 one-parameter listing tool with an output schema, the description covers source scope and the no-invented-ids guarantee. It is incomplete regarding include_mock behavior and result ordering/pagination, which an agent may need before calling.

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_mock has 0% schema description coverage, but the description only alludes to MOCK fixtures in the source list. It does not explain what include_mock controls or what changing its default true value does, so the parameter remains under-specified.

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 gives a specific verb and resource ('List tasks') and narrows scope to tasks from connected read-only sources, naming concrete source categories. It is clear what the tool returns, though it does not explicitly distinguish itself from the sibling get_task_info.

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 explicit guidance on when to use this tool versus get_task_info or other siblings, and no when-not conditions. The read-only task-listing purpose is implied, but the agent must infer the selection criteria.

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

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

With no annotations, the description carries the entire burden and does so: isolated per-run worktree copy, upstream project never written with pre/post SHA-256 manifests, timeout kills the process tree and yields TIMEOUT rather than a false 'no path exists', idempotent retries via request_id, and single-run concurrency. This is exactly the mutation-safety and failure-mode context an agent needs.

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?

Front-loaded with the action and its scope, then parameter notes, then the return/poll hint and concurrency rule. Every clause is informational, but the dense semicolon-chained parameter block makes it slightly harder to scan than a cleanly structured description.

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 an asynchronous, sandboxed, mutating planning job with an output schema present, the description covers initiation, isolation guarantees, timeout behavior, idempotency, concurrency, and the polling handoff. Nothing an agent needs to invoke it 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%, and the description compensates fully for all four parameters: task_id naming pattern, planner whitelist ['Lazy_PRM'] applied to the worktree config, time_budget_seconds bounds 10-1800 with default 120 and expiry semantics, and request_id's regex plus idempotency 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?

States a specific verb and resource ('Start ONE real offline planning run for a New_Design seed task') with clear scope: one run, seed task namespace, isolated worktree. The terminal clause 'poll get_plan_status' plus 'Only one real run at a time' separates it from the read-only sibling tool that reports results.

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 gives clear usage context: form the task_id as 'ND-SEED-<seed>', start the run, then poll get_plan_status rather than waiting. It also states the concurrency constraint ('Only one real run at a time'). It stops short of explicitly excluding alternatives such as validate_motion, so it is not a full when/when-not statement.

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

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

With no annotations, the description carries the full burden and does so well: it discloses that NEW runs return NOT_RUN, that planning success is never treated as PASS, and that verdicts are never transferred to new paths. It stops short of explicitly stating read-only/side-effect-free behavior, though 'Report' implies it.

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?

Front-loads the purpose, then layers result semantics and finally the run_id format. Dense but each sentence contributes; minor cost is the slightly run-on clause about sha256 binding.

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 an output schema exists (return values needn't be described), the description covers purpose, result semantics, and the required parameter's format. An agent has enough to invoke it correctly without further clarification.

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 provides 0% description coverage for run_id, so the description must compensate. It does, specifying accepted forms: local 'R-*' runs and historical record paths like 'rm_next_015_fr69b_transfer_expansion/Q1_RRT_E1' or '.../REF_T1_CM2B_P0'.

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?

States a specific verb ('Report') and precise resource ('the independent-validation status bound to a run's candidate path'). This clearly separates it from siblings like get_plan_status or get_experiment_report, which concern planning/report state rather than validation verdicts.

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?

Explains the meaning of results in two distinct scenarios (NEW local runs vs. frozen research-audit records), which implies when the output applies. However, it never explicitly routes the agent away from alternatives such as get_plan_status, leaving the when-to-use decision to inference.

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