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

Annotations only cover safety (readOnly/destructive=false); the description adds real behavioural context beyond that: the scan list is read live at query time (hence ordering effects), the two numbers can diverge, missing domain knowledge is reported as missing activation, and — importantly — an indeterminate measurement is reported as exactly that, explicitly warning the agent not to read it as 'not activated' or as an all-clear.

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 core question it answers, then layers in the sibling distinctions and failure semantics. Nearly every sentence earns its place, though the conversational framing adds some length for a single-parameter read tool.

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 one-parameter read tool with no output schema, the description covers purpose, sibling boundaries, live-read timing effects, and the three-way outcome semantics (findings / not activated / indeterminate) that an agent needs to interpret the response 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?

Only one parameter (domain) and schema description coverage is 100%, so the schema already carries the meaning. The description adds no format or syntax detail about the domain argument, so the baseline 3 applies.

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: the itemised findings (Einzelbefunde) of the LAST ACTUALLY RUN turbometrics scan, each with a recommended action, plus that scan's overall value. It also names the two siblings it is not — get_performance_score (cached nightly value) and get_performance_alerts (open monitoring warnings).

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 explains the condition under which this differs from get_performance_score, notes that a run triggered via start_performance_scan will appear here first, and routes the agent to get_performance_alerts for open warnings. When/when-not/alternatives are all present.

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