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

Annotations already declare readOnly, openWorld, and idempotent, so the bar is lower. The description adds behavioral nuance beyond annotations: the live window turns over in about two minutes, recent reads may have aged out, and the error distinguishes staleness from typos. This gives an agent expectations beyond the structured hints.

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?

The tool's unique ordering and behavioral caveats are front-loaded: purpose is in the first sentence. Though longer than typical, each sentence earns its place — why this tool exists, what id forms are accepted, what temporal edge case to expect, and which sibling to use instead. Nothing 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 simple one-parameter read tool, the description covers the decision context, the exact input format, the failure mode around the time window, and alternative sibling tools. It also promises the result is exactly that row and nothing else. No critical operational knowledge is missing.

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 100% for the single parameter, so baseline is 3. The description adds some context about 'cite the handle, pass it back here' and the live-window behavior, but the core meaning — accepts full correlation id or short CWF handle — is already fully captured in the schema. No significant uncompensated gap.

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?

Opens with 'Fetch one signal by its id, when you already know which one you want' — a specific verb, resource, and access pattern. It explicitly contrasts with the other read tools that return bounded sets, so get_signal is clearly distinguished from get_latest_signals, search_signals, and get_related_signals.

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 says when to use this tool: when you already know the id and want exact re-read of one row. It names alternatives and gives routing rules: search_signals or scope_signals to find signals, get_related_signals to get signals about the same subject. It even explains why using other read tools for a single row is problematic (row budget re-query).

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