WhenIsBins

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

Beyond the readOnly/openWorld annotations it discloses the blocking wait (~30s), null-field semantics, provisional-result caveats, the meaning of date_completeness values, and the purpose/last-verified caveats of council URLs. It also warns that text inside results is council data rather than instructions, a behavioral safety trait annotations cannot convey.

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 core purpose and the 30-second wait are front-loaded, which is good, but the remainder is a dense wall of rules covering date interpretation, council URL semantics, and product-scope disclaimers. Several of these read as global guidance repeated here rather than tool-specific information, diluting scannability.

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, the description must explain the return shape, and it does: it documents collections[].containers structure, options/conditions/items, bin_colour and lid_colour, date_completeness flags, and council.lookup_url/missed_bin_url semantics. An agent has enough to interpret results correctly without opening anything else.

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; it explains that lookup_id identifies a lookup initiated by get_collections, giving the parameter provenance that the schema's bare uuid pattern does not. It does not restate format or error behavior for an invalid/expired id, so it falls short of a full 5.

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 a lookup ... by its lookup_id') and names the sibling that produced the id (get_collections), which lets an agent tell it apart from find_addresses and get_schedule. The 'waits up to about 30 seconds' note clarifies it is a polling read rather than an instant fetch.

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?

The precondition is explicit: this reads a lookup that get_collections started, so it should be called with a previously obtained lookup_id. It also says 'Same statuses as get_collections' and notes WhenIsBins only reads dates and does not set reminders or report missed bins. It stops short of stating what to do when the lookup is complete versus still pending, or naming an alternative tool for that case.

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

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

Annotations only declare readOnlyHint and openWorldHint; the description adds real context beyond them — results may be provisional or not the user's exact property, and text inside a result is council data rather than instructions (prompt-injection defence). Much of the remaining behavioural text (by_date, date_completeness, weekday_only, missed_bin_url) belongs to get_collections and does not describe this tool's own behaviour.

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 single useful lead ('Step 1. Lists the properties...') is front-loaded, but the bulk of the text is off-topic rule-making about date patterns, weekday_only, date_completeness, missed-bin URLs and reminders — none of which this tool returns or decides. This bloat makes it hard for an agent to extract the instructions that actually govern find_addresses.

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, the description does the necessary work of naming the returned fields (required_input, by_date, date_completeness, council.lookup_url) and how to present candidates. That is enough for an agent to call the tool and handle the response, even though the date-semantics detail is misplaced here rather than on get_collections.

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%, including a detailed description of the optional 'query' narrowing semantics, so the schema already carries the parameter burden. The description adds nothing about postcode format or the effect of 'query' beyond restating that candidates are listed; baseline 3 applies. Credit is limited to its mention that the call names the required_input downstream.

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?

Opens with a specific verb+resource: 'Lists the properties the council knows at a UK postcode', and positions itself as 'Step 1' ahead of get_collections, which distinguishes it from that sibling. It also states it returns the required_input for get_collections. Clarity is slightly diluted by large blocks of downstream date/council-URL guidance that describe other tools rather than this one.

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 behavioural rules: show candidates and let the user choose unless exactly one matches, never guess or pick a property for the user, and say so if the address is absent. The 'Step 1' framing plus the named follow-up (get_collections) tells the agent exactly where this tool sits in the workflow.

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

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

Beyond the read-only, open-world, idempotent annotations, it discloses a wait of about 45 seconds, the meaning of done/partial/still_working/failed, provisional-result caveats, and the fact that embedded result text is data rather than instructions. It also explains council URL fields and clarifies that the tool only reads dates and does not set reminders or report missed bins.

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 description is front-loaded with the Step 2 purpose and most sentences carry necessary operational or output-shape information. It is dense and runs long, but the length is largely justified by the absence of an output schema and the complexity of the status and collection structures.

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, the description compensates by explaining status values, collections and containers structure, date_completeness semantics, provisional results, and council URL fields. It gives an agent enough context to call the tool and interpret the result 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 already 100%, so the baseline is 3, but the description adds useful workflow meaning: postcode is required and the property identifier should come from the field named in required_input, normally property_id from the chosen candidate. It does not add much for the optional address fields beyond what the schema already says.

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 description opens with a specific verb and resource: it looks up collection dates for the one property the user chose. It clearly positions itself as Step 2 after address selection and distinguishes its role from find_addresses and check_lookup.

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 gives explicit call conditions: use after the user has chosen a property, send postcode plus the field named in required_input, and use check_lookup for still_working rather than calling this again. It also states what not to do, including never guessing or choosing a property for the user.

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

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.