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

The description adds meaningful behavioral detail beyond the readOnly/idempotent annotations: it documents the `esito` field, warns that `preambolo` is not the article, clarifies that `abrogato` is informational, and explains `vigenza_storica` as non-current text. This is exactly the kind of output-behavior context 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?

The description is dense but every sentence earns its place: first the core function, then the routing guidance, then the critical output caveats, then the historical-date parameter. The use of semicolon-separated `esito` values keeps it compact without losing clarity.

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 read-only lookup tool with an output schema already present, the description provides enough context to select and invoke it correctly. It covers input semantics, uncertainty handling, special output states, and historical-date behavior, so no critical operational gap remains.

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 0%, but the description compensates well: `fonte` is explained as name/alias with examples, `articolo` is explained as number with extension, and `vigenza` is explained as a YYYY-MM-DD historical date. All three parameters receive meaningful semantics.

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 states a specific action: reading an article by source name/alias and article number, including extension forms like "21novies". It also positions the tool against siblings by naming normattiva_trova_fonte as the pre-step for uncertain aliases and implying article lookup by name rather than by URN.

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 explicitly tells the agent to use normattiva_trova_fonte first when the alias is uncertain, and labels this tool as the reliable path for historical codes. It also gives clear operational guidance around checking `esito` and providing a `vigenza` date for historical text.

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 readOnly/idempotent annotations, the description adds critical runtime caveats: the agent must check `esito`, a 200 response may still be only a preamble, and abrogated or historical-validity results are not current law. These are exactly the kind of behavioral warnings that prevent incorrect interpretation of results.

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 three concise sentences with no filler. The first sentence states the core operation, the second adds essential result-interpretation guidance, and the third routes to an alternative tool. Every sentence earns its place and the most important information is front-loaded.

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?

Given that this tool has one simple parameter, rich annotations covering read-only/idempotent/non-destructive behavior, and an output schema, the description covers the key operational nuance and sibling routing. It tells the agent what to verify in the response and warns about false positives. Nothing critical is missing for correct invocation.

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 schema provides no description for the single `urn` parameter (0% coverage), so the description must compensate. It adds meaningful context by calling the URN 'completo' and specifying that it was 'ottenuto altrove', which differentiates it from source/article inputs. It does not include a URN format example, but for a single simple parameter this is adequate.

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 action, 'Legge un URN completo ottenuto altrove', clearly defining the tool as reading a complete Normattiva URN obtained elsewhere. It also distinguishes itself from the sibling normattiva_leggi_articolo by clarifying that source-plus-article requests belong to that tool. The purpose is unambiguous and well differentiated.

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 explicitly states when this tool is appropriate: when a complete URN is already available. It also gives a concrete alternative, instructing the agent to use normattiva_leggi_articolo for source-plus-article queries because that tool uses the verified table. This is clear direction with a named alternative.

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 mark the tool as read-only and idempotent. The description adds meaningful behavioral detail: verifica=true calls the API and can return 200 for wrong URNs, verifica=false is local and does not prove existence or validity, and warnings about repealed acts or preambles must not be ignored.

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 dense sentences with no filler. The core purpose is front-loaded, verification behavior is explained next, and the operational warning closes the description efficiently.

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 output schema covers return values, and the description supplies the most important caveats: false 200 responses, local versus API verification, and warning handling. A small gap remains around the expected formats for fonte, articolo, and vigenza, but the overall picture is sufficient for an agent.

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 0%, so the description must compensate. It thoroughly explains the verifica parameter and its default behavior, but it leaves fonte, articolo, and vigenza to be inferred from their titles and domain knowledge.

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 'Costruisce [testo](permalink)' without including full text. This clearly distinguishes the tool from siblings like normattiva_leggi_articolo, which presumably retrieves article content.

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 context clear: use this tool when you need a Markdown citation link, not the full article text. It does not explicitly name sibling alternatives or state when not to use it, but the scope is evident.

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?

The description discloses a key behavioral trait not captured by annotations: it does not use the network and operates on local state ('Non usa la rete', 'stato locale'). It also explains what the report contains (real requests, cache hits, errors, density, cooldown), which is useful context beyond the readOnly/idempotent/non-destructive annotations. There is no contradiction with 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?

Two short sentences, with the most important fact (no network, local state) front-loaded and the usage guidance placed second. There is no filler, repetition, or irrelevant detail.

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 zero-parameter, read-only status tool with an output schema present, the description is complete: it says what the tool does, that it is local, what metrics it shows, and when to invoke it. No return-format explanation is needed because the output schema already covers that.

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 has zero parameters, so the description has nothing to explain. Per the baseline for parameterless tools, a score of 4 is appropriate; the description does not attempt to invent unnecessary parameter detail.

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 states a specific verb ('Mostra' / shows) and a clear resource: local state of quota, cache, and cooldown, along with daily aggregates. It also distinguishes itself from the sibling lookup tools by explicitly saying it does not use the network ('Non usa la rete'), making its role as a status/health tool unambiguous.

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 gives explicit timing guidance: use it before an activity with multiple consultations ('Usalo prima di un'attività con più consultazioni'). It does not name alternatives or exclusions, but this is clear, actionable context for an agent choosing between this status tool and the sibling legal-research 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 declare readOnly, idempotent, and non-destructive. The description adds valuable behavioral context beyond annotations: the tool searches only a local table without network access, and it cautions that the local table is not a complete representation of the legal order. This helps the agent calibrate expectations about result completeness.

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 three sentences, each earning its place: first defines the action and scope, second gives usage guidance with rationale, third states a critical limitation. It is front-loaded with the core purpose and contains no filler.

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 tool with an output schema and annotations covering safety, the description is complete. It covers what the tool does, its offline/local scope, when to use it, what caveats apply to the result, and the meaning of the sole parameter. Nothing essential 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 coverage is 0%, so the description carries the burden. It compensates by indicating that the 'testo' parameter is the 'nome o alias' to search for in the local table. While it does not provide format examples or edge cases, it gives the essential semantic meaning for the single parameter.

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 states a specific verb ('Cerca') and resource ('tabella locale'), and lists the searchable attributes: 'tipo, data, numero, allegato e stato'. It distinguishes the tool from network-based siblings by explicitly noting it works 'senza rete', making its offline nature clear.

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 gives explicit usage context: 'Usalo prima di un codice storico' and warns that 'un allegato indovinato può puntare a un atto diverso'. It also provides a clear limitation ('Una fonte assente qui non è assente dall'ordinamento') which functions as when-not-to-conclude absence. It does not name sibling alternatives, but the context is sufficient.

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