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

With only basic annotations (readOnlyHint=true, destructiveHint=false), the description carries substantial behavioral weight and delivers: 30-day retention and auto-purge, early eviction at capacity cap, explicit statement that entries are 'never written to a database', id instability across replays, and evictedCount semantics. It adds far beyond annotation-safe signal without contradicting the readOnlyHint.

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?

Every sentence earns its place — the return-shape, retention, eviction, and durable-handle facts all matter — and the core purpose is correctly front-loaded. However, the entire body is one dense unbroken paragraph, mixing return-format, lifecycle, capacity, and sibling semantics, which harms scannability. Breaking the detail into short sections or bullets would serve an agent far better.

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?

DLQ semantics are genuinely complex — fan-out multiplicity, ephemeral identity, lifetime eviction counts, retention windows — and there is no output schema or sibling annotations to offset the burden. The description covers the response shape, every row field's meaning, how to identify requests durably, and how to reconcile with get_request and get_dlq_entry. An agent can correctly interpret the results of a call from this text alone.

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 for the two pagination parameters is 100%, with limit/offset defaults and bounds already documented in the schema, so the baseline of 3 applies. The description confirms pagination by mirroring limit and offset in the return payload shape, but it adds no extra guidance about how to page through results or how limit/offset interact.

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 opening sentence states a specific verb and resource — 'List entries currently in this project's dead-letter queue, newest first.' Combined with the naming of siblings get_dlq_entry, discard_dlq_entry, and retry_dlq_entry, an agent can clearly distinguish a read/list operation from lookup, discard, and retry without opening their schemas.

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?

The description explicitly routes the agent to alternatives: it explains that get_request still answers for purged/evicted/discarded entries' inbound requests and that get_dlq_entry accepts a requestId lookup. It also preempts confusion by calling the fan-out behavior that produces multiple DLQ rows per inbound request. It stops short of an explicit when-not-to-use statement, so I deduct one point.

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