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

With no annotations, the description carries the whole burden and does well: it discloses the authorization envelope (ordinary warnings fall inside the existing user task, destructive ones do not), warns against label guessing, and explains the waiting_for_dialog follow-up flow. It falls short of a 5 because it does not say what a successful click returns or how to tell a rejected click from an applied one.

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?

Four sentences, front-loaded with the action, then prerequisites, then safety boundaries, then recovery. Every sentence carries distinct information, though the safety sentence is a dense run-on that packs several policies into one line.

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-required-param mutation tool with no annotations and no output schema, the description supplies the missing safety profile, the snapshot freshness prerequisite, and the post-dialog recovery path. Only the return shape and failure/error semantics remain unaddressed, which is a modest gap.

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

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

Schema coverage is only 25% — just 'reason' is documented — so the description must compensate, and it only partially does. 'Requires a fresh snapshot' implicitly ties snapshot_hash to freshness and 'observed button' implies button_id must come from get_revit_dialogs, but dialog_handle and button_id formats/sources are never spelled out.

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: click one observed button in the managed Revit modal dialog. It is clearly distinguished from get_revit_dialogs (which produces the snapshot it consumes) and from get_revit_operation_result (which it defers to after a waiting_for_dialog result). An agent can tell which tool to reach for without opening any 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?

Explicit prerequisites (requires a fresh snapshot from get_revit_dialogs), explicit exclusions (do not guess labels; do not automatically authorize deletion, discarded edits, overwrites, or auth/security permissions), and an explicit routing rule (after waiting_for_dialog, retrieve the original operation result rather than repeating the model command). Both when-to-use and when-not-to-use are covered.

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 two negative behaviors (does not launch Revit, will not attach to a manually opened instance) that are exactly the side-effect risks an agent would worry about. It also names the return fields. It stops short of describing failure behavior when no managed instance is running, which is the main remaining unknown.

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

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

Two short sentences, front-loaded with the core action and scope, followed by the concrete reported fields and the key exclusion. No filler.

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-param, no-output-schema status tool, the description covers what it reads, what it returns (worker PID, model, view), and what it will not touch. Only the behavior when no managed instance exists is left unstated.

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 takes zero parameters, so there are no semantics to explain; the description correctly adds no param noise. Baseline 4 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?

The description gives a specific verb (check) and a precisely scoped resource (the isolated managed Revit 2020 instance), then names the fields reported. This is more precise than the bare tool name implies, though it doesn't explicitly contrast with get_revit_operation_result, which an agent might confuse with a status check.

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 "without launching Revit" and "Never connects to an existing manually opened Revit instance" – the agent can infer this is a safe probe of the managed instance rather than an action on the user's own session. There is no explicit statement of when to prefer this over the sibling get_revit_operation_result, so the agent must infer the boundary.

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, so the description carries the disclosure burden — and it does: it explains that the tool works even when the main API is blocked, that it also surfaces recently auto-handled warnings, and that dialog text is untrusted data, a valuable security caveat. It stops short of noting whether reading dialogs alters dialog state or what happens to unhandled dialogs.

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?

Four short sentences, each earning its place: capability, payload, prompt-injection warning, and usage trigger. The blocking-resilience and returned-contents facts are 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?

The tool takes no parameters and has no output schema, so the description's enumeration of return contents (messages, buttons, hashes, recent auto-handled warnings) fills exactly the gap an agent would otherwise have. An agent has everything needed to decide when to call it and what to expect.

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?

Zero parameters, so per the baseline this is a 4. The description correctly asks nothing of the caller and needs no parameter documentation.

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+resource: inspect modal dialogs of the managed Revit instance, and enumerates the returned content (messages, buttons, snapshot hashes, auto-handled warnings). Sibling differentiation is implied rather than explicit — inspection is contrasted with clicking via 'before asking the user to click routine Revit warnings', but click_revit_dialog_button is never named.

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

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

'Use this before asking the user to click routine Revit warnings' supplies a clear trigger condition and an implied alternative pathway (user clicking). 'Even when its main API is blocked' clarifies the operating context in which this tool is the right choice. No explicit exclusion or named alternative tool, so not a 5.

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 disclose meaningful state-machine semantics (waiting_for_dialog, outcome_unknown) plus retry-safety rules that would otherwise cause duplicate writes. It does not say whether the call blocks or waits, nor what the returned result contains, leaving some behavioral 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?

Three short sentences, front-loaded with the core action and immediately followed by the safety constraints. No sentence is redundant or padded.

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?

With no annotations, no output schema, and 0% parameter coverage, the description leaves the agent without return-value structure or parameter meaning. The retry-safety guidance is strong, but an agent still cannot tell what the result object holds or how to use wait_ms.

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% for two parameters, so the description must compensate and it does not. operation_id is only obliquely implied by 'the original Revit operation', and wait_ms — including its 0–30000ms range and whether it blocks — is never mentioned.

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 the result of the original Revit operation, scoped to after a modal dialog is resolved. This is distinguishable from siblings like get_revit_automation_status and get_revit_dialogs, though the differentiation is by implication rather than an explicit contrast.

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 clear conditional guidance: do not repeat a model write on a waiting_for_dialog result, and inspect the model before retrying after outcome_unknown. It lacks an explicit statement of when to prefer this over get_revit_automation_status, so it stops short of full when/when-not/alternative coverage.

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, so the description carries the full load; it earns credit for disclosing the significant side effect that the managed instance and its bridge are started automatically if needed. It does not say whether the call blocks until the model opens or returns immediately for later polling, nor what happens on incompatible/missing files, both of which matter for a process-spawning mutation.

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?

Three short sentences, front-loaded with the action and target, then the automatic-provisioning note, then the exclusion. Nothing is redundant or padded.

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?

There is no output schema and no annotations, and the description never addresses what the call returns or how to learn whether the open succeeded — a real gap given that get_revit_operation_result exists as a sibling. It is otherwise adequate for a single-parameter 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?

Only one parameter with 100% schema description coverage, so the schema already defines the path and its Revit 2020 compatibility requirement. The description repeats 'absolute path' without adding format examples, expected failure modes, or other 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?

A specific verb ('Open') plus resource ('existing RVT or RFA') scoped to a named environment ('separate managed Revit 2020 instance'). The closing sentence rules out interaction with the user's other Revit instances, which cleanly separates this tool from the status/dialog siblings that operate on the automation 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?

It gives clear conditions for use: an existing absolute RVT/RFA path, target Revit 2020, managed instance. It also states a negative condition ('Does not connect to the user's other Revit instances'). It stops short of routing the agent to siblings such as get_revit_operation_result for retrieving the outcome.

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