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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered without the description. The description contributes one useful behavioral fact beyond that — that each entry is paired with detection guidance, i.e. the payload is prescriptive, not just a name list — but says nothing about scope, ordering, or how many modes appear.

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?

One short sentence with zero padding and the key content (detection guidance) front-loaded. It is slightly under-specified rather than over-long — adding a verb such as "lists" would cost no words but gain clarity.

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 zero-parameter, read-only tool with annotations carrying the safety profile, the description covers the essentials and hints at return contents. With no output schema, a clearer statement of what a caller actually receives (a reference list vs. diagnostic output) would close the remaining gap.

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, and the description correctly implies a single unfiltered catalog with no arguments. Baseline 4 applies for a no-parameter tool; nothing in the text misleads about inputs.

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?

"Agent failure modes with how to detect each" conveys the resource and its content shape (detection guidance per item), but it is a bare noun phrase with no verb, so the agent must infer that this enumerates/returns a catalog rather than taking an action. It also gives no cue distinguishing it from the sibling rescue_failure, which is the closest adjacent concept.

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?

There is no when-to-use guidance, no prerequisites, and no routing hint to alternatives. With rescue_failure sitting in the sibling list, an agent could plausibly invoke either and gets no help from the description.

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