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

Annotations only declare readOnlyHint; the description adds substantial behavior: bounded raw CloudWatch window fetching with local filtering when context/preset/noise flags are set, broad-query caps with truncatedQueryCount signaling a narrower follow-up, and default limit bounding. It also discloses runtimeProvenance semantics (settings.json primary, log-line fallback, conflict reporting, confirmed-only trust) that no structured field conveys.

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 purpose and exclusions, but it is a dense monolith that repeats the same 'one batched queries call with errors/orders/strategy searches' instruction twice in near-identical form, and repeats the invalid-id list that the backtestId schema field already contains verbatim. Strong content, notable redundancy.

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 an 11-parameter tool with 9% schema coverage and no output schema, the description supplies both the response shape (logs, perQuery counts, totalLines, scannedLines, returnedLines, scanned window timestamps, noiseSuppressedLines, truncatedQueryCount, nextToken, paginationWarning) and the runtimeProvenance contract. Nothing an agent needs to call it correctly and interpret results 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 coverage is 9%, so the description must carry the load, and it largely does: query/contextLines/noise suppression relationship, all four diagnosticPreset values explained individually, queries as a batched alternative to query, limit near 1000 for diagnosis, startTimeIso/endTimeIso range filtering. Gaps remain — `sort` is never mentioned and nextToken/pagination semantics are only implied through output fields.

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?

Opens with a specific verb+resource+scope: 'Fetch runtime logs for an identified historical backtest simulation,' and immediately draws the boundary against live/paper bot and scheduled-deployment logs. An agent can distinguish it from get_deployment_logs, get_backtest_artifact, and query_csv 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?

Explicitly states when NOT to use it (get_deployment_logs for deployment runtime logs, list_deployment_artifacts/query_deployment_artifact for decisions) and enumerates the exact question types it answers (errors, tracebacks, startup lines, fills, broker messages, 'why did this fail'). It also mandates evidence gathering before code edits and names the concrete batching pattern.

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