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

Beyond annotations, the description discloses that the returned watch is initially 'not_computed', that alerts only arrive on following calls ('next_call' delivery), that unknown constraints stay uninterpreted, and that auth is required (token_required). Pricing and plan-gating (free_watch_used, plan_ending, 409 destination) are unusually thorough. It is consistent with readOnlyHint=false, idempotentHint=true, and destructiveHint=false.

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?

The action statement is correctly front-loaded, but the body is a semicolon-chained run-on mixing billing, error codes, and auth into one dense block. Every fact is relevant, yet the packing hurts scanability — the pricing sentence in particular is a long clause sequence.

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 a 9-parameter mutation with a billing dimension, the description covers auth, return-state semantics, alert delivery, error-code routing, and pricing, and an output schema already handles return shapes. Little an agent needs to call this 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 78%, so the baseline is 3, and the description adds genuine meaning: level semantics ('NEED default when need is given', CATEGORY needs a process and no need), process 'deduced from the need when absent', the single allowed delivery mode, and current_choice_name resolution behavior ('exact unique matches resolve, others stay unlinked').

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 names a specific verb ('Opens a watch') and resource ('a need'), scoped to 'the organisation of the token', and clarifies the NEED vs CATEGORY mode. It does not explicitly name sibling tools like get_watch/list_watches/unwatch_need, so differentiation relies on inference, but the core action is unambiguous.

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?

It implies usage via mode conditions ('CATEGORY follows a process', 'any process accepted', 'NEED (default when need is given)') and free-plan limits, but never states when to choose watch_need over search_solutions, set_current_choice, or unwatch_need. Error-code passages explain failure states rather than invocation guidance.

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