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

It adds useful non-structural context: the panel self-updates, should not be reopened after each command, and results should be read via scene/screenshot tools, plus the note that an already-accepted shared session can become selected. However, annotations declare readOnlyHint=false and destructiveHint=true while the description frames this as pure inspection with no invitation or access grants, and never explains what could be destroyed or mutated. For a tool flagged destructive, that unexplained gap is material.

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 definition is not front-loaded: the opening two sentences are instructions about open_blender_view and panel behavior that belong to a different tool, and only the third sentence states this tool's purpose. Several clauses ("Do not reopen it after each command") are operational guidance unrelated to invoking get_connection.

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 parameters and no output schema, the description carries the burden of describing the return value, and "Returns connection/session state" is thin given the enumerated scope (account, computers, invitations, friends). The boundary statements and sibling routing help, but an agent still cannot tell what fields or objects come back.

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 the baseline applies and the description is not required to explain any input meaning. It does implicitly define the scope of what is inspected (account access, selected computer, own/shared computers, invitations, friends).

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 core sentence is specific: "Inspect this chat's account access, selected computer, own/shared computers, incoming invitations and friends without opening a visual panel" plus "Returns connection/session state." That is a clear verb+resource with an enumerated scope. It loses a point because the first two sentences describe a different tool (open_blender_view / panel behavior) rather than this one, so the reader must dig past irrelevant framing.

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 routes to alternatives by condition: check_connection for Bridge/Blender health, get_setup_status for setup blockers, get_app_state for Desktop configuration, open_blender_view for the interactive panel. It also states a negative boundary ("does not create an invitation or grant new access"). Not a 5 because the alternatives are listed without saying what this tool returns that those do not, leaving some overlap ambiguity (e.g. get_connection vs check_connection vs view_connection).

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