Take unsummarised items from the queue

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

Annotations declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the safety profile is partly covered; the description adds substantially more with the lease mechanics — other agents skip leased items and unfinished work returns to the queue only on expiry. It also discloses the return payload and explains the 'video: needs a transcript' / 'post: needs the page' hints, plus a prompt-injection warning about treating page content as data. The one gap is that it does not say whether a lease can be released early or what happens if the caller crashes mid-lease.

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, then usage constraint, then lease rationale, then return shape, then per-hint decoding and the next step — a sensible ordering with no filler. It runs long, and the hint-decode sentences are dense mid-paragraph, but every sentence carries operational information rather than restating the schema.

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?

There is no output schema, and the description compensates by describing the return value (a writing brief with language, depth, folders and rules, plus items with urls and chat context, or nothing when empty). For a queue-leasing tool with one optional parameter, nothing needed to call it correctly 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 100% and the schema already documents the 1–10 range and default of 5, so the baseline is 3. The description still earns credit by explaining the tradeoff behind the value: asking for more than you can finish wastes items because they stay leased to other agents until expiry.

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 — 'Reserve items nobody has summarised yet' — and immediately narrows scope to login-walled posts and videos driftnet could not read. It explicitly separates itself from driftnet_search_items, so an agent can pick the right sibling without opening either 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?

Gives an explicit positive condition ('only when asked to work the driftnet queue'), an explicit exclusion with the alternative ('to look things up use driftnet_search_items'), sizing guidance tied to the 30-minute lease, and a follow-on workflow ('open the url, find the tool it is really about, then call driftnet_enrich_item'). This is about as complete as when-to-use guidance gets.

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