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

Annotations already cover read-only, idempotent, non-destructive, closed-world behavior, so the description only needs to add content context. It does: it says the result includes per-source last-sync timestamps and any sync error, which is behaviorally useful. It slightly repeats 'Read-only' and says nothing about result ordering or volume, keeping it from a 5.

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 short sentences, front-loaded with what is returned, then when to use it, then sibling routing, then the safety note. Every sentence carries distinct information and there is no 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?

With no parameters, no output schema, and rich annotations, the description supplies exactly what is missing: what fields come back (sources, sync times, errors) and how this tool relates to its siblings. An agent has everything it needs to call it correctly.

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?

The tool takes zero parameters, so there is no parameter meaning to add; the baseline for a 0-param tool applies. The description correctly doesn't invent any parameter guidance.

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 ('Read') and resource ('which data sources the player has connected'), then enumerates the concrete sources covered (RFEG, Garmin, TrackMan, Strava, Morris Golf app, WAGR) plus sync timing and errors. It also names the three closest siblings and how each differs, so an agent can distinguish it without opening any 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?

Gives an explicit trigger ('Use it before saying their data is missing') and routes the agent to alternatives with their selection conditions: connections_line for a one-line version, connect_link to fix a missing source, get_connection_status for what the MCP connection itself may do. Nothing is left to inference.

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