TrovaStorage

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuine behavioral value beyond them: results are ordered nearest-first and each entry carries address, sizes, published price or "su richiesta", its page and a quote-request link. It does not discuss auth or any behavior when no location is supplied, keeping it short of a 5.

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?

Each language half is well front-loaded (mode, then usage, then filters, then return shape), but the entire text is duplicated in Italian and English, doubling length with zero new information. The redundancy costs an agent tokens without adding clarity, which is a structural flaw rather than a benefit.

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 an output schema present, the description need not detail return values, and it still does so usefully. It covers both location modes and all meaningful filters. The one gap is that zero parameters are required, yet the description never says what happens on an empty call or how limite (default 10) shapes results.

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 the schema already documents all eight parameters, including the mq semantics the description repeats verbatim ("only centres that declare that size"). The description does not mention limite at all and adds no format or interaction detail beyond what the schema provides, so 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 (find self-storage centres/depositories) and spells out the two distinct search modes: by Italian city (with optional district) or around a coordinate point. An agent can immediately tell this is the listing/search tool as opposed to the detail tool (dettaglio_centro) or the price tool (prezzi_citta).

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?

"Use it when a list of centres in a place is needed" gives a clear positive trigger, and the two-mode phrasing implicitly signals when each input style applies. However, it never names an alternative tool or states when-not to use this one, so the agent must infer the boundary with dettaglio_centro.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond them: it enumerates the data actually returned (hours, sizes, price, phone, listing status), notes the provenance/date metadata per field, and explicitly excludes photos and box availability — a genuine scope contract.

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?

Each language version is front-loaded and information-dense with no filler. The cost is the full Italian/English duplication, which doubles the length, though it is a deliberate bilingual convention rather than padding.

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?

An output schema exists, so return-value structure need not be explained, and the description still helpfully enumerates the content scope and its exclusions. With annotations covering safety and a single fully documented required parameter, the definition is complete for correct invocation; only the absence of routing to sibling tools for the excluded data leaves 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 100% and the single parameter is documented in the schema with a pattern and a concrete example (`milano/milano-certosa`). The description only restates that the slug comes from `cerca_centri`, which the schema description already says, so it adds no meaning beyond the structured field. Baseline 3 for full schema coverage.

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 ('Legge la scheda di un centro' / reads one centre's listing) and immediately scopes it to a single centre identified by slug. It cleanly distinguishes itself from the sibling search tool by naming `cerca_centri` as the source of the slug, so an agent can tell lookup from search 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?

Explicit trigger: 'Usalo dopo una ricerca' / 'Use it after a search', with the slug provenance pinned to `cerca_centri`. It also defines what the tool does not cover (photographs, unit availability), which nudges toward other tools, but it never names an explicit alternative for those cases (e.g. prezzi_citta, stima_metratura).

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 the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the lower bar applies. The description adds genuinely useful behavior beyond that: the fallback `dato non disponibile` on small samples and the explicit instruction to quote no figure in that case.

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-loads purpose, then usage, then the failure mode — good ordering with no filler. The content is duplicated verbatim in Italian and English, which doubles length but serves bilingual discovery rather than padding.

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?

Complete for this complexity: annotations carry the safety profile, an output schema covers the return shape, and the description adds the one thing structured fields don't convey — the no-data fallback and the instruction to withhold figures. Nothing needed to call it 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 description coverage is 100%, so both `citta` and `mq` are already documented with format examples and bounds. The description only implies the unit-size dimension ("per misura del box") and adds no syntax or constraint beyond the schema — baseline 3 is appropriate.

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 ("legge"/reads) and resource ("l'ultimo indice dei prezzi del self storage") scoped to an Italian city, plus the exact dimensions returned (min, median, max by unit size, sample counts, month). This is clearly a price-index lookup, distinct from the centre-search siblings, though it never names them for explicit contrast.

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 an explicit trigger ("Usalo per rispondere a «quanto costa un box a…»") and a clear when-to-skip rule for the small-sample case. It stops short of naming the alternative tools (cerca_centri, dettaglio_centro) for the "find a unit" intent, so no real exclusion map.

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