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

Annotations already declare this is a non-read-only, non-destructive, closed-world mutation. The description adds real behavioral context beyond that: the feed runs autonomously with 'no model involved', an unknown slug has the side effect of starting tracking for a new metric, and the call may return `needs_confirmation`. It does not, however, explain scheduling failure modes or what happens on a later conflicting feed.

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?

Front-loaded with the tool's purpose, then three compact functional sentences covering slug semantics, the preview prerequisite, and the backfill follow-up. Every sentence carries information, though the 'Tell the user they can backfill' clause is more agent-behavior guidance than tool description and slightly dilutes the focus.

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 10-parameter mutation with nested mapping/schedule objects and no output schema, the description covers the important operational surface: cadence, the mapping-confirmation prerequisite, the slug side effect, and the `needs_confirmation` return signal. It leaves the nested mapping and schedule fields entirely to the schema, which is a modest gap given the nesting.

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 60%, so the schema carries most of the burden. The description's only parameter statement ('metric takes an id or a snake_case slug; an unknown slug starts tracking that metric') largely restates the schema's own description for `metric`, adding the side-effect note but nothing about mapping, schedule, toolArgs, or windowHours. Baseline 3 is appropriate.

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 and resource ('Freeze a tool call as a metric's standing source') and immediately characterizes the mechanism (runs on cadence, records findings, no model involved). It is immediately distinguishable from siblings like ledger_feeds_preview and ledger_feeds_run, which are named in the same breath.

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 explicit sequencing instructions: confirm the mapping with ledger_feeds_preview first, then tell the user about ledger_feeds_backfill afterwards. The prerequisite and follow-up alternatives are named with the condition that selects each, leaving nothing to inference.

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