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

Annotations already declare readOnly and idempotent, so the safety profile is covered. The description adds genuine behavioral context beyond that: chronological ordering, the message catalogue, and the meaning of inbound (true = the user's engine sent it), which materially affects interpretation of results.

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?

Three compact sentences with no filler; the return-shape description is front-loaded, then paging, then intent. Every clause carries information.

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 usefully enumerates the returned fields (seq, timeUtc, inbound, msgType, raw FIX, parsed tags) and covers pagination. It omits sessionId semantics and error/empty-log behavior, a minor gap for a two-parameter read tool.

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 50% (sessionId undocumented), so the description needs to compensate. It explains afterSeq semantically — 'the last seq you saw' — which is more actionable than the schema's 'seq greater than this', though sessionId's semantics remain entirely implicit.

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 FIX message log for a sandbox session — and narrows scope with 'oldest first' plus the exact message classes (logons, heartbeats, orders, exec reports, rejects). This is clearly distinct from siblings like sandbox_get_orders or sandbox_get_status.

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?

'Use this to explain what happened on the wire' gives a clear purpose context, and the afterSeq sentence defines the incremental-polling pattern. It stops short of naming an alternative tool or an explicit when-not-to-use condition, so it does not reach 5.

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