Apprised.news

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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds meaningful context beyond that: headlines are third-party reporting collected automatically, not written or verified by the site, and each carries its outlet and original URL. It does not mention rate limits or result-cap behavior when filtering reduces the pool, 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?

The purpose and provenance are front-loaded, and no sentence is filler. The final sentence packs three distinct behaviors (minutes windowing, comma-separated keyword matching, wildcard, whole-window scope) into one dense clause, which slightly hurts scannability.

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, return values need not be described, and the definition covers defaults, filtering semantics and data provenance. What remains unstated is how this differs operationally from search_site for keyword lookups, a minor gap for a 3-parameter read 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?

Schema description coverage is 100%, so the baseline is 3. The description does add some nuance the schema lacks: the query is matched over the whole window and a * acts as a wildcard, plus the no-argument defaults. These are useful but largely restate what the schema already defines for limit and minutes.

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 ("latest headlines from the Corvus Intel news corpus") plus ordering ("newest first") and identifies the exact surface it mirrors (the site's breaking ticker and Breaking view). That framing distinguishes it from siblings like get_brief, get_daily_report and search_site without the agent needing to open 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 documents the no-argument default (last 3 hours, 15 items) and how each argument changes behavior: minutes widens/narrows the window, query filters by keyword. It stops short of naming when to prefer search_site or get_brief instead, so routing between siblings is still left to inference.

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 adds genuinely non-obvious context: the content is AI-generated fictional persona analysis rather than reporting, and the payload is truncated to a bounded size with a URL to the full brief — both important for how an agent should present results. It does not mention auth, rate limits, or what happens on missing dates.

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 opening clause is well front-loaded and the disclaimer is valuable, but the full desk-key enumeration duplicates the schema verbatim and consumes a large share of the text. Structural logic is one long sentence with parenthetical pile-ups rather than scannable segments.

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 and 100% parameter coverage, most structured burden is carried elsewhere, and the AI-content disclaimer fills the key gap for a 3-parameter read tool. Still missing is selection guidance against three close siblings and any handling note for absent desk/date combinations.

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 enums and the date pattern are already fully documented. The description's desk list is a verbatim restatement of the schema enum and adds no new semantics; it says nothing about how desk, date and cadence interact (e.g. whether cadence changes the meaning of 'latest').

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 the specific resource ('One Apprised.news desk brief') and enumerates what it contains (lead, analyst takes, synthesis, watch items, sources). It is clearly a single-record fetch, implicitly distinct from the list_briefs sibling, but it never names that sibling or the get_daily_report alternative.

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?

No when-to-use guidance. The description never explains how to choose between get_brief, list_briefs, get_daily_report, or get_breaking_news, nor does it say what to do when a requested desk/date has no brief. Usage must be inferred entirely from the name and schema.

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 this a safe, idempotent, closed-world read, so the bar is lower — yet the description adds two things annotations cannot convey: the payload is trimmed to a bounded size with a URL to the full page, and the content is AI-generated analysis rather than news reporting. It does not mention rate limits, but the truncation and provenance disclosures are the substantive behaviors 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?

Front-loaded with what the tool is and what it corresponds to, then variant details in parallel structure. The local-variant sentence is dense and runs long, but every clause describes an actual output characteristic 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?

Output schema exists, so return values need not be spelled out, and the description still covers truncation, provenance, and both variants. The one omission is routing guidance relative to the sibling report tools, which is the remaining gap for a zero-required-parameter tool with three siblings.

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 already 100%, but the description still adds real meaning for the type parameter by enumerating what each variant contains and explaining the local variant's dedup and LOW-confidence rules. The cadence parameter is left entirely to 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?

Names a specific resource and origin — the structured daily report Apprised.news publishes, the same payload /api/get-report serves — and then splits it into two named variants ("intel" cross-desk report with its sections, "local" Local Wire). An agent knows exactly what payload it receives before opening the 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 type variants give implied selection guidance (default intel vs. state/local press), but the description never contrasts this tool with the closely related siblings get_brief, get_breaking_news, or list_briefs. The agent must infer which report tool to call from names alone.

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 adds real context beyond them: result ordering (newest first), the fields each entry carries, and the important caveat that the content is AI-generated analysis rather than news reporting.

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 opening clause and the Local Wire routing are front-loaded and earn their place. However, the full desk-to-label mapping is copied verbatim from the schema's enum description, consuming roughly half the text without adding information an agent doesn't already have.

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 the definition needn't detail return values, and it covers the non-obvious bits an agent needs: ordering, the AI-generated content caveat, and the Local Wire exclusion. The only meaningful omission is failing to link the returned URLs to get_brief.

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 both enums are documented in the schema, so the baseline applies. The description only re-lists the desk enum verbatim (pure duplication) and says nothing about how cadence changes results or how limit interacts with ordering.

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 ('Recent briefs from one Apprised.news desk, newest first'), plus the concrete shape of each item (date, lead headline, URL) and the backing endpoint. It also carves out a sibling by naming Local Wire as a report and routing to get_daily_report.

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 exclusion and alternative: Local Wire is not a desk brief, use get_daily_report with type "local". It does not mention get_brief, the obvious next step for opening one of the returned URLs, which would have completed the workflow 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?

Annotations already declare read-only, idempotent, closed-world behavior, and the description goes beyond them by disclosing the result cap (5), ranking (best match first), and the fallback to main pages when nothing matches. It also names the underlying index (llms.txt/sitemap), which tells the agent what corpus is actually searchable.

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 verb and resource, and every clause carries information (content types, index source, result cap, ordering, fallback). The second sentence is dense and slightly run-on with the parenthetical about llms.txt and sitemap, 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?

For a one-parameter read-only search with an output schema present, the description covers the essentials: what corpus, what ranking, how many results, and what happens on a miss. The only meaningful gap is routing guidance relative to the sibling retrieval tools.

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% with a single required 'query' string and examples already in the schema description, so the schema does the heavy lifting. The description adds only that matching is by keyword, which is marginal beyond what the schema states.

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 pages on apprised.news by keyword') and enumerates the content types covered (desks, briefs, digests, dossiers, methodology, policy). It never names or contrasts with the sibling tools (get_brief, list_briefs, get_daily_report), so an agent can't tell from this text alone whether to search or fetch directly.

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 word 'Find' and the keyword framing; there is no explicit when-to-use or when-not-to-use statement. It also doesn't say to prefer list_briefs/get_brief once a specific page is known, which is the obvious alternative path among the siblings.

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