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

Annotations declare destructive/non-idempotent/open-world, and the description adds genuinely new behavior: changes skip historical backfill, allow_private governs provider processing of private memory/contacts/objectives, and 'automatic' confines workers to standing user scope. These are material traits not derivable from annotations.

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?

Reasonably sized and front-loaded ('Opt in or out...'), but several sentences are telegraphic fragments ('Use current revision.') and 'Global flags still apply' is vague filler. Dense but 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?

For a destructive, 6-required-parameter mutation with no output schema, the description covers backfill and privacy behavior but omits what destruction actually entails, mode-by-mode effects, and connection requirements. Adequate but with clear gaps.

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 43%, so the description must compensate; it usefully explains allow_private, revision usage, and the automatic/mode intent. However mode enum values (off/shadow/suggest), the features list, scope, and connection handling go largely unexplained, leaving real gaps.

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+resource: opt in/out of semantic features. An agent can distinguish it from read-oriented siblings like semantic_status. It does not explicitly name the sibling, but the mutation framing is unambiguous.

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 operative constraints ('use current revision', 'global flags still apply', 'skip historical backfill') but never says when to choose this over semantic_status or what precondition triggers a policy change. Usage is implied rather than stated.

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