Russia–NATO risk ladder

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful domain context (corrections include what was wrong and who reported it), but nothing about pagination, ordering, or result shape beyond that.

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 tight sentence with the resource stated first and the parenthetical clarifying the corrections content. No wasted words, though it could have spent a few words on filtering behavior.

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 reasonably conveys what comes back (significant changes and corrections history). However, it leaves the two undocumented filter parameters and any ordering/limit semantics unaddressed, so an agent cannot fully predict filtering behavior.

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 only 33% — lang has a description but type and limit do not, and the description mentions no parameters at all. With a documented coverage gap, the description needed to explain the type enum values and the limit cap but does not.

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 (the changelog plus corrections history) and enumerates its scope: data, model, site changes and who reported corrections. It is clearly distinguishable from siblings like get_sources or get_methodology, though it never explicitly contrasts itself with them.

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 describes what the changelog contains but gives no when-to-use guidance, no prerequisites, and no routing to alternative tools such as get_forecast_history. Usage is only inferable from the resource name.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered and the description's burden is lower. It adds domain context (published Metaculus probabilities, one annual conversion per observation), but says nothing about default time window, pagination, or what happens when from/to are omitted.

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 dense sentence with no wasted words, and the subject (what the data is) is front-loaded. It is slightly compressed — 'annual conversion for each observation' requires interpretation — but not padded.

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 carries the burden of describing the return shape, and 'annual conversion for each observation' only partially does that. For a parameterized time-series retrieval tool, an agent still lacks guidance on default ranges and result granularity.

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 75%, so the schema already documents most parameters. The description implicitly maps to `series` (the two named threats) and to the 2035 endpoint, but adds nothing about the `to`/`from` format, defaults, or the `lang` parameter, so it does not compensate for the remaining coverage gap.

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 concrete source (Metaculus), the two forecast targets ('attack on European NATO', 'seizure of Baltic territory' — matching the two enum values of `series`), and the 2035 horizon, so the resource is identifiable. It does not, however, distinguish this from the sibling `get_other_forecasts`, which is what would push it to 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?

There is no explicit when-to-use guidance and no alternative is named, even though `get_other_forecasts` sits right next to it in the toolkit. Usage can only be inferred from the subject matter, so the agent gets no help routing between the two forecast 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 readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful non-annotation context: results are ordered newest-first and carry hand-coded tone scores, per-country averages, check dates and links. It stops short of explaining pagination or limit behavior.

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 that front-loads the resource and scope before the return-content details. Slightly run-on, but every clause (tone range, averages, dates, links) carries information.

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 usefully sketches the payload (tone values, averages, links, dates) and the ordering. Remaining gaps are minor: no default/behavior note for limit and no pagination guidance for a list 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 coverage is 50%: lang and country are documented, but limit and dimension have no schema description. The description partially compensates by explaining the military-vs-hybrid tone dimensions and the 12-country scope, but says nothing about the limit parameter's default or behavior.

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 (public intelligence assessments by governments/services), its scope (12 countries), and ordering (newest first). It is clearly distinct from siblings like get_forecast_history or get_sources, though it does not explicitly name them for 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?

The description never says when to reach for this tool instead of get_sources, get_forecast_history, or get_overview. Usage is only implied by the resource name; no exclusions or selection criteria 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is fully covered by structured fields. The description adds useful behavioral context by disclosing that assumptions carry check dates and that the model has explicit deliberate non-goals, which goes somewhat beyond the annotations, but it says nothing about response shape or scope beyond the listed contents.

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, front-loaded with the resource and its contents. It borders on a run-on list, but every clause earns its place by naming a distinct artifact the tool returns.

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, single-param, no-output-schema tool the description is roughly adequate: it tells the agent what content comes back and confirms the model's deliberate scope limits. It still lacks usage routing and any statement of scope or freshness needed to place it among the six 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 100% and the single enum parameter (lang) is fully documented with allowed values and a default. The description adds no parameter-specific detail, but with zero required params and complete schema documentation, the baseline expectation is met, and the enum constraint is the only param semantic that matters.

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 the resource and enumerates its specific contents (level definitions, formulas, assumptions with check dates, the verbal probability scale, and deliberate non-goals), which clearly distinguishes it from siblings like get_changelog or get_overview. However, the tool name already implies 'methodology' and the description omits a stated verb (e.g., 'retrieve'/'return'), leaving the action implicit.

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 or when-not-to-use guidance is provided. The description never routes the agent to alternatives or states the conditions under which this tool is the correct choice, despite having six sibling tools that could plausibly overlap.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so safety and mutation behavior are covered structurally. The description adds genuine context beyond that: the data carries 'check dates and corrections', which tells the agent results are resolved/graded with provenance. It still says nothing about coverage windows or pagination, so it is a modest add rather than a rich one.

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 that front-loads the resource and then qualifies it with provider names and data traits. Nothing is redundant, though the parenthetical list of five providers is heavy relative to the rest of the sentence.

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, single-optional-param tool with no output schema, the description adequately says what data comes back (forecasts plus check dates and corrections). It falls short on routing — an agent cannot tell from this text when to prefer it over get_forecast_history or how its output differs from get_intelligence_assessments.

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 optional parameter (lang) with an enum and full schema description coverage, so the schema fully documents it. The description adds no parameter guidance, which yields the baseline 3 when the schema does the heavy lifting.

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 resource clearly: prediction-market and other numeric forecasts, naming five concrete providers (Manifold, Polymarket, Metaculus, Good Judgment Open, Atlantic Council) and the scoping qualifier 'a different event or horizon'. What's missing is an explicit contrast with the obvious sibling get_forecast_history, so the agent must infer the division of labor from the 'other' wording.

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 'with a different event or horizon' implies this tool covers forecasts outside the primary set, which hints at when to reach for it, but there is no explicit when-to-use statement and no named alternative ('use get_forecast_history for ...'). Usage is implied rather than prescribed.

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, idempotentHint, and openWorldHint=false, so safety and determinism are covered. The description adds a useful provenance trait (published / model / manual labeling on every number), which is real behavioral value beyond annotations, but does not address aggregation method, caching, or freshness.

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 imperative "Start here," then efficiently enumerates the returned content in two tight sentences. No waste, though slightly dense with enumerated dimensions.

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 optional-param read-only overview tool with full annotations, the description covers content scope and provenance adequately. The main gap is disambiguation from siblings with overlapping-sounding content, which an orientation tool arguably should address.

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 enum parameter fully documented in the schema, so the baseline is 3. The description adds nothing about the lang parameter or default behavior 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 specific content: annual risk for five escalation levels across three time horizons plus intelligence tone per country. Clear what resource is returned, though it doesn't explicitly differentiate from get_risk_ladder or get_intelligence_assessments, which appear to cover overlapping 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?

"Start here" gives a strong implied usage cue for orientation, suggesting this is the entry-point tool. However, it does not explicitly say when to use this versus siblings like get_risk_ladder or get_intelligence_assessments, leaving the agent to infer overlap boundaries.

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/idempotentHint already covering safety, the description adds real behavioral context: output differs by date path, future dates additionally return cumulative risk from the data date, and past dates use archived rather than modeled data. It stops short of describing the ladder's level structure or result shape.

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 sentences, front-loaded with the core scope before the past/future branching and the optional what-if note. Dense but every sentence carries information; only minor tightening is possible.

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 7-parameter read-only tool with no output schema, the description covers the date-range constraint, the two data paths, and the extra cumulative-risk output for future dates. It does not explain what the risk 'levels' are or how the what-if parameters interact, but the essentials for correct invocation 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?

Schema description coverage is 100%, so the schema already documents all seven parameters, including the scenario enum/number union and each what-if percentage. The description only adds the grouping concept ('optional what-if assumptions'), which is a mild aid, not new parameter meaning — 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?

The description names a specific resource ('annual risk of each level') and scopes it precisely to a date window relative to the data date, which is more than a restatement of the title. It does not, however, explicitly distinguish itself from sibling tools such as get_forecast_history, even though past dates pull from the 'published forecast archive' — a boundary an agent would need spelled out.

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 clearly states the internal routing rule (past dates -> forecast archive, future dates -> scenario model) and notes that what-if assumptions are optional, which is the main decision an agent faces. It offers no guidance on when to prefer this over sibling tools like get_forecast_history or get_other_forecasts.

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), and the description adds genuinely new behavioural context: the result set is a bounded catalogue of 51 entries and the fields each entry carries. It stops short of stating ordering, defaults, or how the limit interacts with a 51-item set.

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 tight sentences: the return payload is front-loaded and the filtering options follow. No filler, though the clause 'with what each says, how it is used' is slightly loose phrasing for what is a list of fields.

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 takes on the burden of describing returns, which it does. However, for a 5-parameter tool with 0 required parameters, it omits any mention of limit (capped at 60 against a 51-source set) and lang, leaving an agent unclear on pagination and localisation behaviour.

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 only 20% (only lang is documented), so the description must compensate. It does explain three of five parameters — type (with its values), country, and text (query) — but says nothing about limit or lang, leaving the pagination behaviour of this bounded list 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 resource (a fixed catalogue of 51 sources) and enumerates what each record contains (statement, usage, countries, check date, link), so the agent knows exactly what comes back. It does not explicitly differentiate itself from siblings like get_methodology or get_overview, but the resource is distinct enough to be 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?

It names the three filter dimensions (type, country, text) which implies when the tool is useful, but gives no when-not guidance, no prerequisites, and no reference to alternative sibling tools for adjacent content. Usage is implied rather than directed.

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