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

Annotations already declare the mutation/safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the bar is lower. The description still adds real behavioral context beyond that: the operation is model-free, an unknown slug silently starts tracking a new metric, and the call 'May return needs_confirmation'.

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-loads the core purpose, then flow, then return behavior in a compact block with no filler. Dense but efficient; each sentence carries information the agent needs.

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-param tool with nested objects and no output schema, the description covers the essential behavioral surface (purpose, preview/backfill sequencing, needs_confirmation return). It leaves detailed nested structure (mapping/schedule) to the schema, which is acceptable since annotations carry the safety profile.

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 60%, so some params are documented but not all. The description meaningfully expands `metric` (accepts an id or snake_case slug; an unknown slug starts tracking), which the schema only partly conveys, but it says nothing about the other required/optional params (mapping, schedule, windowHours, approvalId, toolArgs).

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 ('Freeze a tool call as a metric's standing source') and immediately explains the mechanism ('runs on the cadence you give and records what it finds, with no model involved'). This clearly separates it from siblings like ledger_feeds_run (one-off) and ledger_feeds_preview (validate before creating).

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?

Names two alternatives with explicit conditions: validate first with 'ledger_feeds_preview' and offer backfill afterwards with 'ledger_feeds_backfill'. This routes the agent through the correct setup sequence rather than leaving it to inference.

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