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

With no annotations, the description carries the burden and does disclose a meaningful behavioral trait: it never reports 'no device involved' without showing what was checked. However, it does not explicitly state read-only status, permissions, error behavior, or return structure beyond that guarantee.

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 sentences, front-loaded with the core comparison and followed by a useful behavioral guarantee. No filler, though the second sentence could be slightly more precise about what 'cosa è stato controllato' includes.

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?

The description states the purpose and one output guarantee, which is adequate for a simple comparison tool with fully documented parameters. However, with no annotations and no output schema, it leaves return format, read-only safety, and inventory source implicit.

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?

All three parameters are fully described in the schema (100% coverage), so the baseline is 3. The description does not add syntax, format, or matching semantics for produttore, modello, or seriali beyond what the schema already provides.

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 names a specific verb ('Confronta') and resources ('seriali di un avviso di sicurezza (FSN)' and 'inventario'), making the tool's function clear. It does not explicitly contrast with siblings like cerca_apparecchi, so it falls short of a 5.

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 purpose implies the tool is used when checking FSN serials against inventory, but there is no explicit when-to-use, when-not-to-use, or named alternative. The second sentence is a behavioral guarantee rather than usage guidance.

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?

With no annotations present, the description carries the full burden and does well: it declares this is a write operation, that the result is a DRAFT work order, and that approval/closure/assignment happen elsewhere. It omits permission requirements and what is returned (e.g. the new order ID), which keeps it from 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?

Three short sentences, no waste; the creation statement is front-loaded, followed by the confirmation requirement and then the exclusions. Every sentence earns its place.

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 simple three-required-parameter creation tool with no annotations and no output schema, the description covers state semantics, write safety, and scope boundaries. The only gap is the absence of any indication of what a successful call returns (e.g. an order identifier).

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% and the enum for 'tipo' is self-explanatory, so the schema already documents all three parameters. The description adds no parameter-level meaning beyond what the schema provides, making the baseline 3 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 and resource ('Crea un ordine di lavoro') plus the initial state ('in stato BOZZA') and the target system (CMMS). An agent can distinguish this from every listed sibling, none of which create work orders.

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 pre-condition ('chiedi sempre conferma esplicita prima di usarla') and delimits scope by naming what it does NOT do (approve, close, assign). It stops short of naming alternatives for those excluded actions, but no sibling overlaps so the guidance is effectively complete.

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?

No annotations are provided, so the description carries the full burden. It does disclose one genuinely useful behavioral fact - a hard cap of 50 rows - but says nothing about matching semantics (fuzzy vs exact, case sensitivity), sort order, or whether the 50-row cap is a silent truncation with no way to page further (the schema has no paging parameter). That last omission is the most consequential gap.

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 short sentences, front-loaded with the action and followed by the result-size constraint; no filler and no restating of the tool name. It is arguably too terse rather than bloated, which is an under-specification problem captured elsewhere, not a conciseness problem.

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 simple one-parameter search tool with no output schema and no annotations, the description covers the basics but not enough to call it safely: truncation at 50 rows is mentioned without saying whether it is silent or whether results are ranked, and there is no mention of read-only nature or matching behavior. Adequate but with clear gaps.

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 schema field itself enumerates what is searched (serial number, type, model, manufacturer, department). The description adds nothing about the single parameter, so the baseline of 3 applies - the schema does all 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?

States a specific verb and resource: searching equipment in the inventory, plus the shape of the result (at most 50 rows). That is enough to know what the tool does, but it never distinguishes itself from plausible siblings such as apparecchi_coinvolti or report_conformita, so the agent has no explicit basis for choosing among them.

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?

There is no statement of when to use this search versus apparecchi_coinvolti, scadenze, or report_conformita, and no prerequisites or exclusions. Usage can only be inferred from the word 'cerca' and the inventory scope, which is weak guidance given four or five sibling tools operating on the same domain.

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?

No annotations are provided, so the description carries the full burden. It does disclose the concrete set of roots returned, which is genuinely useful, but it never states that this is a read-only, side-effect-free operation, nor that it takes no arguments and is the natural entry point.

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 compact sentence with the resource name front-loaded and the useful enumeration of roots immediately following. Nothing wasted, nothing padded.

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 values needn't be explained, and the zero-argument schema is trivial. The only shortfall is the lack of explicit routing context relative to read_dir and the other siblings, which matters for an entry-point tool.

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 schema baseline of 4 applies; there is nothing for the description to clarify beyond confirming the absence of filtering options.

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 ('Elenca') and resource ('cartelle consultabili'), then enumerates the root categories returned (manuali di service, FSN, report). This lets an agent distinguish it from read_dir, which presumably drills into a folder, though the description never names that sibling explicitly.

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 word 'consultabili' (browsable) and the enumeration of root folders imply this is the top-level entry point before read_dir, but there is no explicit 'use this first / then call read_dir' routing instruction or any excluded 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?

With no annotations, the description carries the full burden; it does disclose one genuine behavioral trait — the operation is confined to configured roots. It says nothing about what happens on an out-of-scope path (error vs empty result), whether listing is recursive, or how hidden entries are treated.

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 short sentences with no filler, and the core action is stated first with the constraint second. It is efficiently sized, though it leans toward under-specification rather than maximum information density.

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 values need not be explained, and the tool is a simple one-parameter read. Still, for a filesystem-facing operation with no annotations, the description omits recursion behavior and out-of-root error handling that an agent would want before calling.

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 already documented as "Cartella da elencare", matching the description's wording. The description adds no extra semantics (relative vs absolute path, root-relative form), 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?

"Elenca il contenuto di una cartella" names a specific verb (list) and resource (folder contents), so the agent knows exactly what the tool returns. The siblings operate on different domains (roots, devices, deadlines, work orders), so no explicit differentiation is needed, though none is offered.

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?

"Funziona solo dentro i roots" implies a prerequisite (discover roots first, e.g. via list_roots) and warns of a scope limit, which is real usage guidance. It does not, however, say when to pick this over siblings or what to do when the path falls outside the roots.

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?

No annotations are provided, so the description carries the full disclosure burden. It does credit a real side effect — writing a CSV into the Report folder — which is the key behavioral fact, but it omits everything else: whether an existing file is overwritten, how the file is named (year?), what permissions or auth are required, and what the tool returns once the file is written.

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 with no wasted words: the computation is front-loaded and the output side effect (CSV in Report) is stated at the end. Nothing is repeated from the schema or title.

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 simple one-parameter report generator this is adequate in purpose, but with no annotations and no output schema the description should say what comes back (file path? summary counts? success flag?) and whether re-running the same year overwrites the previous CSV. Those are the only real gaps for a tool this narrow.

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?

There is one parameter (anno) at 100% schema coverage with a title, range 2000-2100 and the gloss 'Anno di riferimento'. The description adds no further semantics such as whether the year bounds the scheduled-activities period or the execution dates, so the schema 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?

The description names a specific verb (calcola / salva un CSV) plus the resource (attività programmate) and the exact breakdown produced (in tempo, in ritardo, non eseguite), segmented per reparto and tipo di attività. It is fully distinguishable from the siblings (list_roots, read_dir, cerca_apparecchi, scadenze, etc.), though that separation comes from obvious domain difference rather than explicit routing.

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?

Usage is only implied: an agent can infer it should call this when a compliance/execution report per department is requested. There is no statement of when NOT to use it, no prerequisites, and no pointer to alternatives such as scadenze or apparecchi_coinvolti, which might overlap for one-off lookups.

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?

With no annotations, the description carries the full behavioral burden. It usefully discloses that the result is a draft requiring human verification, which is meaningful context beyond the schema, but it says nothing about read-only nature, file-size or format limits, or failure behavior on unreadable PDFs.

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 sentences, no filler, with the core purpose in the first sentence and the critical caveat immediately after. Nothing is buried or 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?

An output schema exists, so return values need not be described, and the single fully-documented parameter is covered. The remaining gap is behavioral detail (read-only guarantee, what happens on malformed input) that an annotation would normally supply but does not here.

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% for the single 'percorso' parameter, which already documents that it is a path to a PDF or text file inside the roots. The description adds no additional meaning about the path format or expected directory, 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?

The description names a specific verb (estrarre) and resource (avviso di sicurezza / FSN), which is unambiguous and distinct from the sibling tools (scadenze, cerca_apparecchi, report_conformita). It stops short of explicitly contrasting itself with any sibling, but the resource specificity is enough for an agent to pick it correctly.

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?

Usage is implied rather than stated: it is the tool for pulling operational data out of a safety notice, and the second sentence tells the caller the output must be verified against the original. There is no explicit statement of when to prefer it over alternatives, nor any prerequisite such as the file being inside the roots.

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?

With no annotations, the description carries the full behavioral burden. It usefully discloses inclusion/exclusion criteria ('non ancora eseguite', 'già scadute oppure in scadenza entro N giorni'), but omits read-only status, permissions, pagination, sorting, and default horizon behavior.

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?

It is a single front-loaded sentence with no wasted text. It is concise and well-structured for the purpose, though it could be slightly richer without becoming verbose.

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 query tool with three optional parameters, no annotations, and no output schema, the description should clarify the result shape and operational behavior. It only gives the filtering scope, leaving return values, sorting, and optional filter interactions unspecified.

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 tipo, reparto, and entro_giorni thoroughly. The description only echoes the N-day horizon and adds no meaning beyond the schema, making the baseline 3 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?

The description names the resource ('attività programmate') and the exact subset it returns: not yet executed, already overdue, or due within N days. It is clear, but it does not explicitly distinguish itself from sibling tools such as report_conformita or cerca_apparecchi.

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?

There is no explicit when-to-use statement, no alternatives, and no exclusions. The deadline scope implies a use case, but an agent is left to infer when to choose this over sibling tools.

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