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

Annotations only say readOnly/openWorld; the description adds the non-obvious behaviors that matter: no new lookup is performed, the no_schedule result path, that date_completeness values mean per-service next-only rather than a complete calendar, that results may be provisional or not the exact property, and that text in results is data not instructions (prompt-injection guard). That is substantial context beyond the annotations.

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 purpose is front-loaded, but the body is a dense run-on mixing return-field semantics, date-arithmetic prohibitions, URL field meanings, and agent phrasing policy. Some content repeats ('never guess' appears twice) and a portion is user-facing wording policy rather than tool behavior.

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, describing the return shape is necessary and largely done: collections[].containers structure, 'or' alternatives, null containers, bin_colour/lid_colour presence, council.lookup_url/missed_bin_url/missed_bin_checked_at. The top-level shape (e.g. by_date) is referenced but not defined, leaving a small gap.

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% (property_id is bare), so the description must carry the meaning — and it does, specifying that property_id comes from a previously returned 'done' lookup and must not be guessed or chosen for the user. It does not add a format example, but the origin constraint is the key semantic.

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 ('Reads the stored schedule for a property_id') and immediately scopes it: 'It starts no new lookup', which separates it from find_addresses/get_collections. The mention of 'an earlier done lookup' returned property_id ties it into the sibling tool flow without ambiguity.

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?

'For a repeat check' gives the governing condition, and the fallback path is explicit: 'if it reports no_schedule, run find_addresses and get_collections again.' It does not say when check_lookup is the better choice instead, so one sibling is left unaddressed.

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