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

With no annotations, the description fully carries the behavioral burden and does so thoroughly: it discloses main-thread execution, temp_override behavior, return serialization, the need to assign result, acceptance of top-level return, and undo-step behavior. This is rich, concrete behavioral context that goes well beyond 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?

The description is compact yet information-dense, with the core action front-loaded and every subsequent sentence adding necessary execution semantics. The example at the end is useful without padding.

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 that there is no output schema and no annotations, the description covers everything an agent needs to invoke the tool correctly: execution context, scope, return formatting, result assignment, undo semantics, and an example. Nothing critical is missing for a general code-execution 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 baseline is 3, but the description adds meaningful nuance beyond the schema: the last expression becomes the returned value, result must be assigned for non-expression snippets, and the undo step is only pushed on successful calls unless undo is false. This goes beyond the simple 'defaults to true' schema note.

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

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

The opening clause 'Execute Python inside the running Blender (bpy)' clearly states the verb and resource. It does not explicitly differentiate from the sibling tools blender_health, blender_viewport, or blender_scene_info, though the general-purpose nature is evident from the first sentence.

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 strong coding guidance ('Prefer the data API over bpy.ops', 'Do not return raw bpy objects') and explains execution context. However, it never states when to choose blender_exec over the sibling tools or when not to use it, so alternative-selection guidance is implied rather than 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?

No annotations are provided, so the description carries the full burden. It discloses that the tool is non-mutating (a reachability check) and lists the return contents, but it does not mention behavior on failure, response format, or whether any state is modified. This is adequate but not rich.

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 two short sentences with no filler. The core action is front-loaded, and the return-value note is directly useful to an agent deciding whether to call this tool.

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 nullary, low-complexity health check, the description provides the essential context: what it verifies and what it returns. There is no output schema, so the explicit return-value summary is valuable, though failure semantics are left unspecified.

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/scenario, and the schema is empty, so parameter documentation is not needed. The baseline of 4 applies because there is nothing for the description to compensate for.

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 uses a specific verb ('Check'), names the resource ('Blender addon bridge'), and clearly distinguishes this from siblings like blender_exec or blender_viewport by framing it as a reachability probe. It also states what it returns, leaving no ambiguity about the tool's purpose.

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

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

The phrase 'Check whether the Blender addon bridge is reachable' implies this is a health/preflight check, but the description does not explicitly say when to use it versus siblings or when not to use it. Usage context is inferable rather than directly 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 of behavioral disclosure. It communicates the read-only nature through 'Summarize', scopes the operation to the open file, and reveals a concrete limit ('up to 200 objects'). It does not describe failure behavior when no file is open, but the core behavior is transparent enough.

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, front-loaded sentence with zero filler. It efficiently communicates the verb, target resource, scope, and a relevant limit in a compact form.

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 tool with no output schema, the description is substantially complete: it states what information is summarized and the object cap. Minor details such as exact return structure or error behavior are not specified, but this is acceptable for a simple inspection 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?

This tool has zero parameters and the schema has no properties, so there are no parameter semantics for the description to compensate for. The baseline of 4 applies because there is nothing missing on the parameter side.

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 action ('Summarize'), the specific resource ('the open Blender file'), and exactly what it covers (scene, mode, collections, and up to 200 objects). This is specific enough to distinguish it from siblings like blender_exec or blender_viewport, even without naming them.

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 when the tool should be used: when a summary of the current Blender scene/collections is needed. However, it does not explicitly state when to use this tool instead of siblings like blender_health or blender_viewport, nor does it mention any 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?

No annotations exist, so the description carries full responsibility. It discloses key behavior: uses OpenGL viewport capture, not a full render engine, and caps the longest edge. As a capture, side effects are minimal, and the non-render clarification is the most important behavioral trait; nothing contradicts.

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 that front-load the action and then add the essential 'not a full render' caveat. No filler 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 single-parameter, read-only capture tool, the description covers what it does and what it avoids. The only minor gap is the lack of explicit output carry-back (file path vs. data), but the PNG output is stated, so it is adequate.

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% with a full explanation of maxEdge (default, max, exclusive minimum). The description adds no parameter details, which is fine under the baseline; no compensation 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?

States a specific verb ('Capture') and resource ('current 3D viewport') with the output format ('PNG') and method ('OpenGL'). The clarification 'Does not run a full render' distinguishes it from a render tool, and the sibling list (health, exec, scene_info) makes it clearly a snapshot utility.

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 context that it captures the viewport rather than executing a full render, which implies use for quick previews. It does not explicitly name an alternative tool or condition, but the scope statement is sufficient given how different the siblings are.

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