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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety and repeatability profile is fully covered and "Read-only" in the description is largely redundant. The one genuinely additive behavioral fact is the active/sold scope; nothing is said about missing-id errors, rate limits, or data freshness. With annotations carrying the burden, a 3 is appropriate.

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?

Two tight sentences, front-loaded with what is returned, zero filler; the final "Read-only" is the only slightly redundant clause and costs almost nothing.

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 exists, but the description plus the schema's `view` documentation adequately convey the returned shape (compact projection vs full GraphQL node). Naming the id source (URL or search result) closes the main integration gap; only error behavior for an unknown id is left uncovered.

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% and both parameters are documented in the schema, including the compact/full enum and id example. The description's id guidance (booli.se/bostad/<id>, residence_id from search) largely restates the schema example, and it says nothing about the `view` parameter. Baseline 3 when the schema does the work.

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?

"Full detail for one property by its Booli residence id" is a specific verb+resource plus the identifier, and the contrast with the search siblings (one vs many) is implicit in the phrasing. An agent can tell this is the single-record lookup rather than a search.

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 states when this applies: it accepts an id from a URL or a search result, and "works for both active and sold properties" removes the ambiguity of whether a separate sold-property lookup is needed. It stops short of naming alternatives or stating prerequisites (e.g. needing an id in hand rather than a query).

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?

Goes well beyond the annotations by enumerating the returned diagnostics (bridge role, port, version, extension link state, elapsed time) and enumerating the failure classes the hint distinguishes (bridge never came up / extension not connected / browser can't serve capability / server-side problem). It also confirms 'no auth required'. This is real behavioral context an agent cannot infer from readOnlyHint/idempotentHint alone.

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?

A single dense sentence plus a short routing instruction, front-loaded with the action and ending with the failure-mode enumeration. The list of diagnostics is long but each item earns its place; the only minor cost is one very overloaded sentence.

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 carries the full burden of explaining what comes back, and it does so comprehensively – listing every diagnostic field and the interpretive hint. Nothing needed to call or interpret this tool 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?

The tool takes zero parameters, so the baseline is 4. There is nothing for the description to disambiguate beyond confirming the call is parameter-free, which it implicitly does by describing a self-contained round-trip.

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 action (round-trips a public booli.se URL through ContextMint Bridge), the exact resource (/graphql), and the nature of the result (diagnostics). It is unmistakably a health/diagnostic tool, distinct from the listing/search/stats siblings, without opening any 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?

Explicitly says when to call it: 'Call this when a real tool fails and you want to know which hop broke.' That is a clear trigger condition and implicitly positions it as a fallback to the other booli_* tools.

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 already establish read-only/idempotent/open-world behavior, so the bar is lower, and the description adds real value: it discloses that metrics are computed over ONE page of results, distinguishes total_count from sample_size, and warns that thin per-metric counts undermine a median. Those sampling semantics are genuine behavioral context beyond the annotations, though auth/rate-limit traits are not addressed.

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 and each sentence carries information (sample reliability, total vs. sample distinction). The mid-sentence em-dash construction mixing input and output field names makes it slightly dense to parse, but nothing is redundant.

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 22 parameters, the description does substantial work by naming the returned metric fields, the row counts behind each metric, and the total-vs-sample distinction — compensating for the missing return-value spec. Some filter semantics still lean entirely on the schema, but nothing critical to calling it correctly is absent.

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 high (82%), so the schema already documents most of the 22 parameters, setting the baseline at 3. The description adds only a little param-level meaning ('page'/'pages' say which page — though no 'pages' param exists), and the field names it explains (sample_size, sold_price_count) are outputs rather than inputs.

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 precise verb and resource — 'Aggregate sold-price statistics (median/average final price, price per m², average over/under-asking %)' — and explicitly anchors it to a sibling ('Takes the same scope and filters as booli_search_sold'). An agent can distinguish this aggregation tool from the listing-returning booli_search_sold without opening either 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?

Clearly frames the tool as the aggregate counterpart to booli_search_sold, so the choice between them is inferable (stats vs. raw listings). It lacks an explicit when-to-use/when-not statement or a named alternative for edge cases, keeping it just below the top tier.

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 already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so 'Read-only' in the description is largely redundant. However, with no output schema, the description adds real value by disclosing the return shape (each area carries an `area_id`), which is the key behavioral fact 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?

A single sentence, front-loaded with the verb and resource, then the downstream handoff, then a safety tag. Nothing is wasted and no clause is buried.

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 two-parameter lookup with no output schema, the description covers purpose, downstream use, and return shape, which is what an agent needs to call it correctly. Minor gaps remain (result ordering, ambiguity handling for multi-match place names), but nothing blocking.

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 description coverage is 100%, so both `query` and `limit` are already documented in the schema (including the default of 10). The description adds no syntax, format, or matching-semantics detail beyond the schema, so the baseline of 3 applies.

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 ('Resolve a place name to Booli areas') and enumerates the entity types returned (municipalities, districts, streets). It also names the sibling tools it feeds (booli_search_listings / booli_search_sold), so an agent can place it in the workflow 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?

The description makes the usage contract explicit: call this first to turn a place name into an `area_id`, then pass that id into booli_search_listings / booli_search_sold. It gives clear context but no explicit 'do not use this for X' exclusion (e.g. resolving non-place inputs).

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 already declare readOnlyHint and idempotentHint, so safety is covered; the description still adds value by disclosing pagination behavior and the total_count/pages fields to inspect in the response, which matters because there is no output schema. 'Read-only' is redundant with the annotation but harmless.

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?

Roughly three sentences, front-loaded with the resource and scope, then filters, then pagination. Nearly every clause earns its place; only the trailing 'Read-only' is filler given the annotation already states it.

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 20-parameter, zero-required search tool with no output schema, the description covers scope, filter families, pagination, and response count fields. Sort/view semantics and input ranges are left to the schema, which is acceptable, but a note on defaults or result limits would complete it.

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 description coverage is 80%, so the schema already documents nearly every parameter, including the area_id-vs-location precedence and enum values. The description adds only a grouped summary of filter categories (price, rooms, living area, plot, object type, construction year), which is the baseline for a well-covered schema.

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 with scope: 'Search active for-sale property listings on booli.se.' The word 'active' plus 'for-sale' implicitly separates it from booli_search_sold, and it names booli_search_areas as the source of area_id, so an agent can route correctly without opening schemas.

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 clear usage context: scope by area_id or free-text location, filter by the listed dimensions, paginate by page. It routes the agent to booli_search_areas for area IDs but never states when to prefer a sibling such as booli_market_stats or booli_get_listing; there are no explicit exclusions.

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 already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the description's 'Read-only' adds nothing new. It does contribute the result content (final price plus over/under-asking %) and pagination behaviour, but says nothing about external-API rate limits, auth, or completeness guarantees for an open-world scraping-style source.

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 resource and its differentiating output, followed by scoping, filtering, pagination and the read-only note in short clauses. Slightly comma-dense in the middle sentence, but every clause carries information.

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 22-parameter, no-output-schema search tool, the description covers purpose, scope selection, filter categories, pagination and the two headline return metrics, leaving the detailed field semantics to an 82%-covered schema. It omits auth/rate-limit context for an external source, which is the only meaningful 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 description coverage is 82%, so the schema already documents area_id vs location precedence, date formats, units (SEK, m²) and sort/view defaults. The description only groups filter categories at a high level (price, date, rooms, area, object type) and adds no semantics beyond the schema — the baseline 3 applies.

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 — searching sold properties (slutpriser) — and names the distinguishing output (achieved final price and over/under-asking %), which cleanly separates it from the active-listing sibling. The phrase 'the comparables for valuation' also tells the agent what this data is for.

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 description implies the use case (valuation comparables) and lists scoping/filter options, but never names or excludes alternatives such as booli_search_listings (active listings) or booli_market_stats. An agent must infer from the word 'sold' that this is the right tool rather than being routed explicitly.

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