FirmaRED · Sellado y verificación

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 the useful behavioral fact that it returns the *full* content (implying search returns partial results), but says nothing about missing-id behavior or error handling.

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?

One front-loaded sentence that identifies the resource, the operation, and the key parameter semantics with zero 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 single-parameter read tool with full annotation coverage and no output schema, the description covers the essentials. The only gap is the not-found/error case, which is minor 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 0% and `id` is an untyped bare string, so the description carries the burden — and it does, clarifying that the id is either a note slug or a verification code. That meaningfully narrows what would otherwise be an opaque string.

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 (trae) and resource (contenido completo de un resultado de search), and anchors it to the `search` sibling by describing what it operates on. It stops short of explicitly contrasting with `verificar` or `oraculo`, but the retrieval-of-search-result framing is 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?

Naming 'un resultado de search' gives clear context: this is the follow-up call after a search returns a hit. No explicit when-not-to-use or alternate-tool routing is provided, but the usage path is unambiguous for this small toolset.

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, non-destructive and closed-world, so the safety profile is covered. The description usefully adds what each item carries — source, sealed ingestion time, and a link to the FirmaRED record rather than the outlet — but says nothing about snapshot freshness, caching, or ordering.

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 the resource front-loaded and no filler; the parenthetical about linking to FirmaRED rather than the outlet earns its place as non-obvious behavior. Slightly clause-heavy but efficient.

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 takes on the job of explaining the return shape and does so (source, sealed timestamp, internal link). Combined with full parameter documentation and safety annotations, the only real gap is freshness/caching semantics.

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%, with both 'n' (1–30, default 10) and 'tema' (word filter on title/summary) fully documented in the schema. The description adds no syntax or behavior beyond what the schema states, 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?

Describes a specific resource (the FirmaRED Hoy front page) and its scope — news from 71 Argentine and international outlets, refreshed to the present moment. It implicitly separates a curated front page from a query tool, but never names 'search' or 'fetch', so sibling differentiation is left to inference.

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 call this versus the siblings (search, fetch, oraculo), nor any exclusion or prerequisite. 'ahora mismo' hints at a live snapshot, but an agent gets no routing guidance from the 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?

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is fully covered without prose. The description adds useful domain behavior — results are time-sealed ("sellados con la hora") and carry an adjudicated status ("el estado que les dio el Juez") — but does not explain whether the seal means immutability, whether results can change retroactively, or what the Judge status values mean.

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 with no filler; the core scope ("para hoy") is stated up front and the qualifiers follow. It is slightly opaque because it leans on in-house jargon ("Oráculo", "Juez", "sellados") without unpacking it, but nothing is wasted.

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 no parameters, the description must carry the return-value story, and it only sketches it: 'predictions', a timestamp seal, and a Judge status. How many predictions come back, what the Judge status distinguishes, and how this differs from the 'hoy' sibling are left for the agent to discover.

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 per the baseline this sits at 4. The description does not need to describe input semantics and correctly refrains from doing so.

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 resource and scope: the Oracle's predictions for today, including a timestamp seal and the Judge's verdict status. An agent can tell this is a read of today's forecast content, but there is no explicit verb and no differentiation from the sibling 'hoy' (also 'today'-scoped), which risks ambiguity between the two.

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 phrase "para hoy" implies a temporal scope but gives no when-to-use reasoning, no exclusions, and never mentions the sibling 'hoy' or when to prefer one over the other. The agent must guess how this differs from an equally today-oriented tool.

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 annotations already declare read-only, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds the return shape (id, título, URL), but says nothing about result limits, ranking, or freshness beyond "noticias recientes".

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: the first says what is searched, the second says what is returned. The key scoping information is front-loaded and there is no redundant text.

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 annotations covering safety, the description covers the sources and return fields adequately. However, the undocumented query parameter and the absence of any result-limit or ranking context leave meaningful gaps 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?

There is one required `query` parameter with 0% schema description coverage, so the description carries the full burden of explaining it. It says nothing about query syntax, language handling, matching behavior, or expected input format, leaving the parameter effectively undocumented.

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 ("Busca") and two named sources ("FirmaRED Hoy" and "las verificaciones públicas"), which lets an agent distinguish this combined search from the more narrowly scoped sibling tools `hoy` and `verificar`. It is clear and concrete, though it does not explicitly contrast itself with those siblings.

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 by the sources named; the description never says when to use this combined search instead of `hoy` or `verificar`, nor when not to use it. An agent can infer the purpose but must guess at routing between siblings.

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 annotations, the description discloses several non-obvious behaviors: the seal is published as a public verifiable fact, the original document is never uploaded (only the hash), the signing keys/algorithms used, and a 20/hour-per-origin rate limit. Notably it describes querying external drand/NIST beacons and a TSA while openWorldHint=false, which sits in tension with the annotation but is not a direct contradiction.

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 and a constraint, with the core action and its guarantee front-loaded; every clause carries distinct information (mechanism, privacy, rate limit). 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 mutation tool with no output schema, the description says a signed act is created and published but not what the caller receives back (receipt, ID, proof payload, URL). An agent that needs to chain into verificar or report the seal reference is left guessing.

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%, so baseline is 3, and the description earns an extra point by clarifying the central parameter's semantics in context — 'No sube el documento: solo el hash' tells the agent the input must be a digest, not content. It adds nothing about quien/titulo, but those are already fully documented in the 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 — seals a SHA-256 hash with a trusted timestamp — and goes further by naming the mechanism (FirmaRED signature, drand/NIST + TSA time sandwich, public verifiable fact). An agent knows exactly what operation this is, though the description never names a sibling (e.g., verificar) to contrast against.

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 context is implied (you seal when you need time-certain proof) and a hard usage constraint is given ('Máximo 20 por hora por origen'), but there is no explicit when-to-use/when-not or pointer to verificar for checking an existing seal. The agent must infer 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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so credit here goes to the added context: accepted input shapes and the three things returned (what it is, when signed, public page). It stops short of saying what happens on a non-matching or invalid code, which matters for a verification tool.

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: the first defines the operation and its input tolerance, the second defines the return. Front-loaded with the verb and resource, with detail trailing behind 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?

With one parameter, no output schema and full annotation coverage, the description supplies exactly what the structured fields cannot: the accepted input variants and the shape of the result. Failure behavior (unknown code, ambiguous prefix) is the only meaningful omission.

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 already names the four accepted forms (code, hash, prefix ≥10, /v/ URL), which the description largely restates. The "10 o más caracteres" precision is helpful but duplicates rather than extends the schema text, 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 ("Verifica un código de FirmaRED") and enumerates what the code can attest to (firma, acta, nota de Hoy, pronóstico, cierre). An agent can distinguish this read/verify path from the signing sibling `sellar` 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?

The verify-vs-sign boundary is implied by the verb and the accepted inputs, but there is no explicit "use this when… / not when…" guidance or named alternative among `sellar`, `fetch` or `search`. Usage is inferable rather than stated.

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