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

With no annotations, the description carries the burden and does well: the 'ls + cat' framing makes it clear this is a read-only traversal, and each level listing its children is disclosed. It also exposes non-obvious truncation behavior (summary.omitted_sections / summary.compacted / summary.hint) that an agent would otherwise misread as missing data; only an explicit 'no side effects' statement is absent.

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 verb and the ls+cat analogy, then a per-tree breakdown, then the sibling routing tip — a sensible priority order. The source enumeration partially restates the schema enum, which is mild redundancy but aids scanning.

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 four-parameter, four-tree tool with version gating, the description covers traversal model, per-tree path conventions, truncation handling, and sibling routing. Return values are covered by an output schema, so nothing critical is missing, though version-selection consequences are left entirely to the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter including the per-tree path syntax and version gating is already documented in the schema. The description adds the conceptual framing that 'source picks the tree', but no syntax or format detail beyond what the schema already provides, so baseline 3 applies.

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 concrete verb and resource ('Browse ITASCA documentation by path') and immediately grounds it in an analogy ('like ls + cat over one documentation tree') that tells an agent exactly what the operation does. It also enumerates the four trees by content type, which separates it from itasca_query_doc and the execution siblings.

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?

Gives explicit routing: use this tool when you have a path, use itasca_query_doc 'when you only have keywords', and notes that query results are paths for this tool, forming a clear workflow. It also advises 'start at the top of a tree when unsure and descend', covering the unknown-path case.

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

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

No annotations are provided, so the description carries the disclosure burden. It does add real value by describing the return content (Python prints and console output interleaved in execution order), but it omits whether the call is read-only/safe, what happens if the task is still running or the ID is invalid, and it leaves the long-poll semantics of wait_seconds entirely to the schema.

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 paragraphs, front-loaded with the purpose and followed by the one genuinely non-obvious detail (output interleaving). No filler sentences, though the parameter advice could have been folded into the first sentence more tightly.

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 formatting need not be explained, yet the description usefully characterizes the content shape. With no annotations, a small gap remains around safety/read-only status and error or task-not-ready behavior, but for a status-checking tool this is close to sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all five parameters are already documented in structured fields; the description only restates skip_newest, limit and filter. It adds no new information about wait_seconds' long-poll behavior or about how filter interacts with pagination ordering.

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 pair ("Check status and paginated output for a submitted Itasca task") and the second paragraph clarifies what 'output' means (interleaved Python prints and console output). It implicitly separates itself from itasca_list_tasks/itasca_execute_task by scoping to an already-submitted task, but never names those siblings explicitly.

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

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

"Use skip_newest / limit to paginate, or filter to keep only matching lines" gives usage for three parameters but says nothing about when to call this tool versus itasca_list_tasks or how to poll a running task. The when-to-use context is implied by 'submitted task' 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?

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses main-thread execution, persistent side effects, blocking until completion or timeout, non-trackability by itasca_list_tasks, inability to interrupt mid-execution, and bridge behavior for command batching and FISH definitions.

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?

It is front-loaded with the core synchronous semantics and well-structured with bullets. The code-writing rules are necessary but lengthy, making it less concise than ideal, though 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?

The definition is complete for a complex code-execution tool with an output schema. It covers environment, runtime semantics, constraints, failure/interruption behavior, parameter handling, and sibling-tool alternatives.

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 the baseline is 3. The description adds meaningful execution constraints for the code parameter, including itasca.command normalization, whole FISH blocks, and program call behavior, plus timeout usage guidance pointing longer work to itasca_execute_task.

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?

It states a precise verb and resource: execute Python code synchronously in the Itasca engine process. It also distinguishes itself from itasca_execute_task by emphasizing synchronous execution and shared engine state.

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

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

It explicitly gives typical uses such as live model inspection, command output capture, parameter tuning, and plot creation. It also names the alternative and condition: cancellable, pollable, or background work should use itasca_execute_task instead.

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

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

No annotations are provided, so the description carries the full burden and does so: it returns a task_id immediately, runs in the background, captures console and itasca.command() output into the task log, and stays interruptible. It further discloses the shared __main__ namespace with itasca_execute_code during cycling, and what happens on violating the FISH-block or program-call rules (engine blocked in interactive FISH mode, bridge warning).

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 purpose, return behavior, and the sibling routing before the long script-writing rules, which is the right order. The scripting-rules section is dense and somewhat lengthy, but each bullet prevents a concrete failure mode rather than restating the schema.

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 shape needn't be explained, and the description still covers the async contract, lifecycle routing, cross-tool concurrency, and script authoring constraints. Nothing an agent needs to invoke this 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 coverage is 100%, so the baseline is 3; the description goes beyond it by constraining what entry_script may contain — FISH definition blocks must be passed whole in a single itasca.command() string, itasca.command must be called by its import name, and program call files are run one command per engine call. That is real added meaning for the primary parameter, though the description parameter itself is unaddressed.

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 first sentence states a specific verb and resource ('Submit a Python script file') plus the execution mode ('asynchronous execution in the Itasca engine'), and later explicitly contrasts with itasca_execute_code for synchronous inline runs. An agent can distinguish it from every sibling without opening a 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?

It names the alternative explicitly ('For synchronous, inline execution, use itasca_execute_code instead') and maps the entire lifecycle to companion tools: check status, interrupt, list. The condition that selects each path is stated rather than inferred.

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 present, so the description carries the full burden — and it does: it discloses the asynchronous acceptance semantics ('Returns as soon as the request is accepted; it does not wait'), the error condition for terminal tasks, and that engine state is preserved rather than torn down. That is exactly the non-obvious behavior an agent needs before calling a mutation 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-loads the action and the async caveat in the first two lines, then layers follow-up, exclusions, and state-preservation notes. No sentence restates the name or title, and each adds a distinct operational 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?

An output schema exists, so return values need not be explained, and the description instead covers the things the schema cannot: async semantics, error states, state preservation, and the correct next tool. For a single-parameter mutation tool, nothing needed to call 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 coverage is 100% and the schema already documents that task_id comes from itasca_execute_task or itasca_list_tasks, so the description is largely redundant here. Its slight value-add is the recovery hint for an unknown id, but that is guidance rather than added meaning about the parameter itself. Baseline 3 applies.

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 ('Request interruption') and resource ('Itasca task') with clear scope: 'pending or running'. An agent can distinguish it from itasca_check_task_status and itasca_execute_task without opening 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?

Names the follow-up tool (itasca_check_task_status) to confirm the stop, the recovery path (itasca_list_tasks) for an unknown task_id, and the exclusion ('Tasks already completed, failed or interrupted return an error'). When-to-use and when-not are both explicit.

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 well: it declares the tool read-only, describes ordering, explains persistence across GUI restarts, and lists returned fields and paging via total_count. It does not cover permission requirements or error behavior, but for a read-only listing tool that is a minor gap.

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

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

The first sentence front-loads the purpose and ordering, and subsequent sentences each add useful information about return fields, paging, persistence, and use cases. There is no redundant restatement of the tool name or schema.

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 the description need not fully explain return values, yet it still enumerates key entry fields and total_count. Combined with clear usage guidance and paging semantics, it is complete for a two-parameter read-only listing 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%, so the schema documents limit and skip_newest. The description adds meaning beyond the schema by explaining how they page over the full history using total_count, which helps an agent use the parameters correctly.

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 ('List tasks tracked by the bridge'), specifies ordering ('newest first'), and distinguishes itself from siblings by naming itasca_check_task_status and itasca_execute_task as alternatives for different tasks.

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?

Explicitly lists when to use it: recovering a task_id from an earlier session, seeing running or recently finished tasks, or checking bridge connectivity. It also names the sibling tools to use for task output and script submission, leaving little inference required.

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 behavioral burden and does provide useful non-obvious behavior: cross-tree searching, source tagging of hits, and source-specific fallback hints when nothing matches. It does not discuss ranking or exhaustive search semantics, but the output schema and parameter descriptions cover result shape and limits.

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

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

The description is front-loaded and compact, with three sentences that each carry useful meaning. The phrases about source-specific hints are slightly dense but still readable and purposeful.

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 search tool with a rich input schema and an output schema, the description gives enough behavioral context to call it correctly. It covers keyword search, cross-source behavior, source scoping, and the handoff path to browsing; remaining details are adequately handled by structured fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds semantic context for source by explaining combined versus single-tree search and fallback hints, but it does not add meaning beyond the schema for query, software, version, or limit.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: searching ITASCA documentation by keywords. It also distinguishes itself from the sibling itasca_browse_doc by explaining that every hit carries a path for browsing. The grep analogy makes the retrieval model immediately clear.

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

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

It clearly explains the two usage modes: omit source to search all four documentation trees, or provide source to search one tree. The relationship to itasca_browse_doc is implied through hit paths, but the description does not explicitly state when to prefer browsing over searching or vice versa.

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