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

Annotations only cover readOnly and openWorld; the description adds real behavior beyond that: newest-first ordering, verbatim IGEPN text, and the instruction to relay safety recommendations exactly as written. It omits rate limits, coverage/latency caveats, and what an empty result means, keeping it below 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?

Front-loads the resource and provenance in the first sentence, then intent examples, then a tidy Args block. Every line is useful, though the phrasing is slightly verbose and the Args formatting leaks into the description body.

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 correctly describes what comes back (bulletin text and special reports, newest first) and how to handle safety content. It leaves minor gaps around time-window semantics and empty results, but is otherwise complete for a read-only alert feed.

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 Args block carries the full load: it documents all three parameters with defaults (hours=48, n=10) and constraints (168=one week, max 50) plus a concrete volcano example ('Sangay'). This fully compensates for the missing schema descriptions.

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+resource ('Recent IGEPN instant bulletins... and special volcano reports') with ordering ('newest first') and provenance ('as IGEPN wrote them'). It does not explicitly distinguish itself from the sibling volcano_status, 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?

Gives concrete trigger queries ('any volcano alerts', 'is there ash from the Sangay', 'lahar warnings') that map user intent to this tool. It never names an alternative or exclusion condition against volcano_status or latest_quakes, so it stops short of explicit when/when-not 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 establish readOnlyHint=true and openWorldHint=false, so safety is covered and the description adds genuine operational context: PRELIMINAR reports appear in ~5 minutes, results may be revised, and `preliminary` preserves the first estimate. This latency/revision behavior is not derivable from annotations or schema.

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 scope, then user-intent triggers, then the caveat and field guidance. Every sentence contributes distinct information (scope, triggers, staleness handling, revision semantics) with no 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?

There is no output schema, so the description must carry return-value burden; it explains the two most decision-relevant fields (`ago`, `preliminary`) and the revision model. Coverage of the full response shape is partial, but the critical caveats for correct use are present.

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 there is no parameter syntax to explain; baseline for a no-arg tool is 4. The description instead directs attention to the fields to inspect in the result (`ago`, `preliminary`), which is more useful than param documentation would be here.

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 scope: 'the single most recent earthquake reported by the IGEPN, with its latest (revised if available) values.' The word 'single' implicitly separates it from the sibling latest_quakes (plural list), but no sibling is named explicitly, so an agent must infer the 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?

Gives concrete trigger phrases ('what was that earthquake just now', 'did it just shake?') and tells the agent what to do when the result is stale: check `ago` and say the report may not exist yet rather than guessing. It stops short of naming latest_quakes as the alternative for multi-event 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely non-obvious behavior: the source is IGEPN, results are newest-first, repeated reports are collapsed to the latest entry per event, and IGEPN labels the NEAREST town — so a place match may miss the city where the quake was felt. That caveat is the kind of operational insight annotations cannot convey.

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 summary sentence followed by a clean Args block; the usage examples earn their place by tying user phrasings to arguments. It is a little longer than strictly necessary, but there is no filler or repetition.

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 still conveys the result shape (one entry per event, latest report, newest first) and documents all four optional parameters including bounds and defaults. Nothing needed to call the tool 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 0%, so the description carries the full burden and does so: hours with a default plus 168/720 conversions, min_mag as a >= threshold with an example, place with case/accent-insensitivity, examples and the nearest-town caveat, and n with default 15 and a max of 50. Every parameter gains meaning absent from 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?

The description states a specific verb+resource (recent earthquakes from IGEPN), the ordering (newest first), and the de-duplication semantics (one entry per event, latest report). That scope plus ordering implicitly separates it from the singular sibling last_quake, so an agent can route without 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?

It gives concrete trigger phrases ('earthquakes today / this week', 'any tremors near Quito?', 'strong quakes this month') that map onto the hours/min_mag/place arguments, which is clear guidance about when to reach for this tool. It stops short of naming alternatives or stating exclusions relative to last_quake / ig_alerts, so it is not a full 5.

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 readOnlyHint/openWorldHint already covering safety, the description adds genuinely non-obvious behavior: IGEPN only publishes periodic reports for volcanoes it actively follows, so unreported volcanoes are absent; the 30-day window for the no-argument mode; and the fallback to a possibly stale report (read `report_date`) plus instant alerts when a name is given.

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 two calling modes and then the Args note, so scanning yields the key decision first. The `volcano` argument is described once in the prose and again in the Args block, which is mild redundancy but not noise.

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?

No output schema exists, and the description largely compensates by enumerating the returned fields (activity levels, trends, report_date, instant alerts). It stops short of describing the structure or formatting of those fields, which is the only remaining gap for a single-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 0%, so the description carries the full burden and does: it defines the parameter as a volcano name, states case/accent/space-insensitivity with three worked examples, and fully specifies the default behavior when the parameter is omitted.

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 resource (latest IGEPN activity report for Ecuadorian volcanoes) and names the exact payload fields (surface and internal activity level, each with trend). Sibling overlap with ig_alerts is preempted by clarifying that instant alerts are only attached when a volcano is named.

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 concrete trigger phrasings ("how is the Sangay", "is Cotopaxi active") and clearly splits the two calling modes: omit `volcano` for every volcano reported in the last 30 days, supply `volcano` for that volcano's latest report however old. It never explicitly routes away from ig_alerts, which is the nearest sibling, so 4 rather than 5.

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