AI Lifeline (read-only observed values)

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

With no annotations, the description carries the full behavioral burden and largely meets it: it discloses the exact return shape (site_status, totals, staleness rule, generation time, per-series fields) and adds a scope disclaimer ('Nothing here judges the observed world'). It omits auth requirements, rate limits, and error behavior for a read endpoint, which are the only remaining gaps.

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?

Purpose is front-loaded and the payload is enumerated compactly; the listing of totals fields is dense but justified given there is no output schema. Slightly over-long for a read endpoint, but no sentence is pure 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 read-only health endpoint with no output schema, the description documents the return payload thoroughly and explains both parameters' semantics. The main omission is authentication/access context, which matters less for a health check.

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, and it does: it enumerates the valid region values ('jp'|'us'|'eu'|'sg') that the schema's bare string type leaves unspecified, and defines only_stale as 'return only series with stale=true'. It does not clarify the null/default behavior for region, so it falls short of a 5.

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 and resource – returning the liveness of AI Lifeline itself from /api/health.json – and enumerates the payload, so the tool's purpose is unambiguous. It does not explicitly name the sibling tools (get_series, list_series, search_series) it differs from, though 'Nothing here judges the observed world' implicitly distinguishes it from those data-reporting tools.

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: the description establishes this as a service-health/monitoring endpoint but never says when to call it instead of the series tools. The region and only_stale filters are explained as behavior, not as conditions selecting this tool over alternatives.

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, and it does disclose useful behavior: values are as published by the site and 'nothing is recomputed', plus it surfaces staleness judgement and checked_at generation time so the agent can judge data freshness. It omits error/not-found behavior and any auth or rate-limit notes, which keeps it short of 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?

Front-loaded with verb, resource, and key format, and the trailing sentence about data provenance is short and earns its place. The middle field enumeration is a dense run-on list, but every item describes a real return attribute 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?

With no output schema, the description must describe the return, and it does so thoroughly (value, unit, observed_at, value_status, source/license/attribution, update frequency, staleness, URLs, checked_at). The remaining gap is failure behavior for an unknown or malformed id, which an agent would benefit from knowing.

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% – the schema only carries a bare 'Series Id' title – so the description must compensate entirely. It provides the full composite key format '<region>/<chapter>/<series_key>', a concrete example, and flags the id as permanent, which is exactly what an agent needs to construct a valid argument.

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 ('Return one series by its permanent id') and pins the scope to a single series, which cleanly separates it from list_series and search_series. The inline ID format and example ('jp/fiscal/jgb_yield') make the purpose unambiguous 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?

The phrase 'by its permanent id' implies this is the lookup-by-known-id path, but the description never states when to use it versus search_series (find the id) or list_series (enumerate). No exclusions, prerequisites, or alternative routing are given.

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 behavioral burden. It does disclose the backing source (/api/index.json) and a passthrough guarantee ("no re-aggregation"), which is useful, but says nothing about pagination, ordering, result size, or any auth/rate constraints on a listing endpoint that could return many entries.

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 data source are front-loaded, and there is very little filler. The single long sentence enumerating return fields is dense but information-dense rather than redundant, so it earns its length.

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 appropriately compensates by enumerating the returned fields (page URL, API URL, answer line, headline value, series ids). Combined with the documented region values, an agent can call this correctly; only ordering/pagination and sibling routing are left uncovered.

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% and the schema only shows an untyped string|null, so the description adds real meaning by naming the allowed values ('jp', 'us', 'eu', 'sg') and marking the parameter as an optional filter. It stops short of saying what region actually filters (chapters vs series) or how invalid values behave, so not a full 5.

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 (List) and resource (the chapters AI Lifeline publishes), and enumerates the exact payload fields returned, so an agent knows what comes back. However, the tool is named list_series yet the description talks about listing chapters, and the siblings get_series and search_series are never mentioned, so the boundary between this tool and its siblings must be inferred.

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: it is the unfiltered index listing ("Returns exactly what index.json and series.json contain; no re-aggregation"), which hints at when to prefer it over search_series. There is no explicit when-to-use, when-not-to-use, or statement of which sibling handles lookups of an individual series.

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 and does well: it discloses case-insensitive substring matching, the underlying endpoint (/api/series.json), that there is no ranking beyond registry match order, and the returned field list. Auth needs and rate limits are still unstated, keeping it short of 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?

A single dense sentence (plus a routing clause) with the search semantics front-loaded and no filler. Slightly run-on, but every clause adds usable information rather than restating the name.

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 two-parameter search with no output schema, the description covers matching rules, return shape, ordering behavior, and the alternative tool. Only edge cases (empty results, large limits, permissions) are unaddressed.

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 and largely does: `query` is defined as words matched case-insensitively against enumerated fields, and `limit` is defined as the cap on returned matches. It never states the default of 20, but the semantics of both parameters are clear.

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 (Search) over a specific resource (published series) and names exactly which fields are matched (series id, name, chapter, unit, source name). An agent can distinguish it from list_series and get_series without opening schemas.

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 routes the agent to get_series when it needs the value, which establishes when this tool is insufficient. It does not explicitly contrast with list_series, so the separation of search vs enumerate is left implicit.

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