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

Beyond the readOnlyHint/destructiveHint annotations, the description discloses that spans carry only relative durations, offsets, and code-defined labels, never absolute timestamps, source, or user values; that a self-scoped token limits visibility to the install; and that absent credentials or a trace the tool returns a note. These are genuine behavioral constraints an agent cannot infer from the schema or annotations.

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 description is dense and front-loads the output shape, then moves to data constraints and credential behavior. It earns its length for a complex tool, but the final 'Read-only.' sentence repeats the annotation and the single long paragraph could be more scannable, so it is not perfect.

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 output schema, the description compensates well by itemizing return fields, data redactions, credential modes, and the no-trace/no-credentials fallback. It slightly loses points because account_token is mentioned without being present in the input schema, and the relationship between install_id/read_token and the hosted account_token is left vague.

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 coverage is 100% and both parameters have thorough descriptions, so a baseline of 3 applies. The description adds value by explaining the consequence of the read_token (self-scoped, returns only that install's spans) and by flagging the hosted account_token path, which is useful beyond the field-level schema text.

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 specifies the resource (a full-stack trace for one user action), the granularity (waterfall of spans with layer, route label, duration, offset, and rating), and the derived outputs (score, summary, slowestLayerRules). This is enough to distinguish it from sibling trace/analysis tools like boosthis_recent_samples or boosthis_session_summary even without an explicit leading imperative verb.

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?

It gives clear operational context: credentials are required, a per-install read token is self-scoped, and missing credentials or no trace yields a note. However, it never states when to prefer this tool over an alternative such as boosthis_recent_samples or boosthis_snapshot, nor names any exclusions beyond missing credentials/trace.

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