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

Annotations already establish read-only, idempotent, closed-world behavior, so the bar is lower, and the description still adds real detail: pagination at 50 per page starting at page 1, the per-item fields returned (state, own words, count of people who came forward, plain-language reason for a turned-away item), and an output-presentation constraint about leading with sentences. It omits error behavior for an invalid `list_id` or an out-of-range page.

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 the primary distinction and dense with information per sentence, but the phrasing is wordy ('being checked and turned away', 'a ready sentence to say'), which costs a little readability for an agent parsing it once.

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 and zero schema descriptions, the description supplies modes, pagination, returned fields, and the mutation escape hatches. Minor gaps remain around ordering of the list summary and handling of empty or invalid pages.

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 0%, so the description must carry the load, and it does: `list_id` is defined by its absence (summary mode) versus its presence (single-list mode), and `page` is given both its origin ('from 1') and the page size (50). No parameter is left ambiguous.

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+resource ('Read your human's own lists') and immediately splits behavior by parameter: one entry per list without `list_id`, the full list with items when given. The two-mode framing makes it unmistakable against siblings like list_intents or read_manual.

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?

Explicitly tells the agent which mode to pick ('With no `list_id`... With `list_id`...') and redirects mutation intents to amend_intent and withdraw_intent. It does not disambiguate against the numeric-sounding sibling list_intents, which is the one remaining routing gap.

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