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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, so the safety profile is partly covered. The description adds genuinely useful context: a cost of 3 MESH/call and the enforcement rule (rejecting mixed visual+access patches). It does not say what a rejection looks like, whether the patch is mutated, or what the tool returns, so it stops short of full behavioral disclosure.

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 short with no filler sentences, which is good, but the telegraphic fragments ('Visual-only first, access decision separate', '(3 MESH/call, a tool · ops)') trade clarity for brevity. The cost/pricing tail is useful; the 'a tool · ops' fragment is noise.

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 non-read-only guard with no output schema, the description leaves key gaps: the expected patch format, whether the check is advisory or blocking, and what the caller receives on pass vs. reject. Given a nested-object payload and openWorldHint, an agent cannot confidently construct a call from this text alone.

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% but the single 'input' object's description is generic boilerplate referencing agent-brain and agent-memory payload shapes, not a Board patch. The description adds nothing about how to shape the patch payload. With one parameter and full nominal coverage, baseline 3 applies, but the schema text does not actually inform this tool's input.

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 checkable behavior: 'checks if a patch touches agent-access controls, and rejects bundling a visual change with an access change.' However, 'Hardens Board changes' is vague and the agent cannot tell whether the tool only inspects a patch or also applies/enforces the change — 'rejects' could mean an error return or an actual block. The core resource (Board patches / agent-access controls) is named, but the verb is muddled between 'harden' and '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?

'Visual-only first, access decision separate' implies a workflow ordering (run this before committing a Board change, split visual from access edits), which is real usage guidance. But there is no explicit when-to-use trigger, no when-not-to-use, and no named alternative among the many mesh_* siblings. Usage must be inferred from a terse fragment.

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