convoy_forget_node

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

With no annotations, the description carries the full burden and does so: it discloses the refusal condition (unfinished delivery), that it names blocking delivery ids for cancellation, that finished results never hold a row, that online rows are never forgotten, and that relayed requests follow the owning host's rules. These are exactly the mutation-safety and side-effect details an agent needs.

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?

Information-dense and front-loaded, with the core action first and constraints following. It is long and packs many clauses into run-on sentences, but virtually every clause (refusal, auto-eviction, bulk equivalent) earns its place, so little is wasted.

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?

No output schema or annotations exist, yet the description covers action, targeting, refusal behavior, blocking-id feedback, auto-eviction context, and the bulk alternative. An agent has everything needed to call this correctly.

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% (host_id documented, node_id not), and the description compensates by explaining host_id's origin (convoy_list_nodes), the omit-for-local default, and the relay behavior it triggers. node_id's meaning is only implied as 'the row,' leaving a small gap.

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 (delete/forget) and resource (a stale node row), and immediately clarifies what a stale row is ('the row a renamed, moved, or deleted project left behind'). An agent can distinguish this from convoy_list_nodes, convoy_cancel_job, and convoy_start_node without opening a 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 explicit when-to-use (cleaning up stale rows), the local-vs-relayed condition governed by host_id, and the automatic alternative ('Rows unseen for a week are evicted automatically; this is the immediate manual path'). It also names the bulk in-TD equivalent (Forget Offline Nodes... button), covering the alternative surface.

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