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

Annotations only declare it is a non-read-only, non-idempotent, non-destructive write. The description adds real behavioral context beyond that: the 409-on-duplicate semantics, the one-override-per-tier uniqueness constraint, the meaning of modifier values (below 1 tightens, above 1 relaxes), and the required scope.

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 dense sentences, each carrying distinct information (semantics, defaults, effect direction, 409 routing, scope) with the core purpose front-loaded. Slightly long, but no sentence is 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 two-parameter mutation with no output schema, the description covers everything an agent needs: what is written, the uniqueness/conflict behavior, the effect of the value, the defaults it overrides, and the alternative path on conflict.

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 both parameters are documented, but the description goes further by supplying the built-in default modifier per tier (critical 0.6, high 0.8, medium 1.0, low 1.4), giving the criticality enum concrete meaning beyond the schema's bare enum list. It does not restate the min/max range that the schema already carries.

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 ('Override the criticality modifier for one tier') and immediately frames rows as overrides layered on built-in defaults. An agent can distinguish this from create_* siblings and from get/list/update/delete_criticality_modifier without inspecting the 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?

Explicitly routes the agent: a duplicate returns 409, so 'call list_criticality_modifiers and update the existing row instead.' It also names the prerequisite scope (los_targets:write), which tells the agent the conditions under which the call will succeed.

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