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 and idempotency profile is fully covered elsewhere. The description adds only the modest detail that keys are 'observed in RUM' (i.e., derived from telemetry rather than configured), and says nothing about auth requirements or result limits.

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?

A single sentence with the scope ('session-level') front-loaded and no filler. Every word contributes to identifying the resource and its domain.

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 read-only listing tool with full schema coverage and no output schema, the definition covers what an agent needs to select and invoke it. It could go further by noting how the returned keys relate to the event-level counterpart or whether results are paginated, but nothing essential 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%, so botId and projectApiKey are already documented in the schema, including the note that the API key is required on every call except a few named tools. The description adds no additional parameter meaning, so the baseline of 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?

The description names a specific verb ('List'), resource ('session-level metadata keys'), and scope ('observed in RUM for TrueCoverage filters'), which lets an agent distinguish it from the similarly named get-truecoverage-event-metadata-keys by the session vs. event granularity. It stops short of explicitly naming that sibling, so it lands just below the top tier.

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?

'for TrueCoverage filters' implies the keys are meant to drive filter construction, but the description never states when to call this versus the event-level metadata keys tool or the related event/child-event-tree siblings. Usage is inferable but not spelled out, and there are no exclusions or prerequisites.

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