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

With no annotations at all, the description carries the full burden and largely drops it. The phrase 'as unverified' does disclose a meaningful behavioral trait about the resulting disposition, but there is nothing about side effects, persistence, permissions, deduplication against existing events, or what 'assessed' state entails for an 8-parameter write-shaped 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?

A single well-formed sentence with the resource and examples front-loaded and no filler. It is concise, though brevity here shades into under-specification rather than economy.

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 return values need not be explained, but with 8 undocumented parameters, zero annotations, and no clarification of what 'assess' or 'unverified' mean operationally, the description is far too thin for the tool's complexity.

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 eight parameters carry only bare titles (breadth, importance, as_of, ends_at, source_url). The description explains none of them — not even the required event_type's allowed values or the default 'high' importance — so the agent must guess at semantics.

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 gives a verb ('Assess') and a resource ('event') and enumerates example event types (CPI, earnings, election), which is more than a tautology. However, 'assess' is opaque about what the tool actually produces or changes, and nothing distinguishes it from siblings like event_readiness or assess_level.

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 event_readiness or upcoming_events, no prerequisites, and no exclusions. The only hint is 'user-supplied', which implies intake of external events but never says so explicitly or names an alternative path.

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, yet it says nothing about side effects, whether this is purely analytical, what the output contains, or how 'as_of' / 'event_id' affect behavior. Only the existence of an output schema offsets this slightly.

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 tight, front-loaded sentence with no filler. It is efficient, but the brevity here is closer to under-specification than true conciseness given the tool's complexity.

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 an 8-parameter analytical tool with zero annotation and zero schema-description coverage, a single sentence is far too thin. The presence of an output schema excuses the absence of return-value documentation, but nothing compensates for the missing parameter and selection guidance.

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% across 8 parameters, and the description only loosely maps 'level' and 'bars'. Critical parameters such as buffer_pct (default 0.03), acceptance_closes (default 3), direction, as_of, and level_name are given no meaning anywhere, so an agent cannot know how the break/rejection decision is tuned.

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 ('Explain') and a specific resource ('a break, rejection, or test at a custom level from supplied OHLCV bars'), which is a distinct and recognizable analysis task. It implicitly differs from the event-oriented siblings (assess_event, event_readiness) by being level-driven, but that contrast is never made explicit.

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 choose this over assess_event or the readiness tools, no prerequisites, and no exclusions. An agent must infer usage purely from the phrase 'from supplied OHLCV bars.'

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 not say whether classification is computed on the fly, what role as_of plays, whether the call has side effects, or what happens for unknown event IDs, leaving significant behavioral gaps for an unannotated 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?

The description is a single front-loaded sentence that enumerates the classification outputs with zero waste. Its terseness is efficient, though it comes at the cost of missing usage and parameter detail.

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 are covered, but the description lacks any explanation of the two parameters, usage conditions, or behavioral traits. For an unannotated tool with 0% schema description coverage, this leaves the agent under-informed about how to invoke it correctly.

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 for undocumented parameters, but it never mentions event_id or as_of. A reader can infer event_id is the catalyst and as_of is a reference date, but the description adds no explicit meaning, format, or constraints.

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 verb ('Classify') and resource ('one catalyst') and enumerates the five output categories, so an agent knows exactly what the tool returns. It does not distinguish itself from close siblings like assess_event or options_readiness, leaving ambiguity about which classification tool to pick.

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 when-to-use guidance, no exclusions, and no mention of alternatives such as assess_event or upcoming_events. The agent must infer from 'one catalyst' that this is for a single event, but nothing tells it when this classifier is preferable to sibling 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?

No annotations are provided, so the description carries the full burden, and it reveals almost nothing: it never says whether the tool only reads evidence or also records a readiness state, what 'complete enough' means (criteria, thresholds), or what happens when evidence is missing. The output schema covers return values, but the behavioral profile of the call itself is undocumented.

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 front-loaded sentence with zero filler. It is efficient, though the brevity leaves the substance to the other dimensions rather than wasting words.

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 9-parameter evaluation tool with no annotations, the definition is too thin: it never explains the readiness criteria, which evidence categories are required, or how the optional numerics influence the verdict. The presence of an output schema offsets only the return-value burden, not the invocation guidance.

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?

With 9 parameters and 0% schema description coverage, the description must supply parameter meaning and supplies none. An agent cannot tell whether implied_move_pct, bid_ask_width_pct, maximum_loss, etc. are thresholds to compare against, overrides, or merely echoed values - a critical ambiguity for correct invocation.

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 ('Check') and object ('event and options evidence') with a clear goal: readiness for human review. It does not distinguish itself from the sibling 'event_readiness', leaving an agent to guess whether the difference is the inclusion of options data or something else.

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?

'Complete enough for human review' implies this is a gate to run before a review step, which is useful implied usage. But there is no explicit statement of when to prefer this over event_readiness or assess_event, and no preconditions or exclusions 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?

With no annotations, the description carries the full behavioral burden. It hints that results are 'curated' and have 'coverage limitations,' but does not specify what those limitations are, whether results are exhaustive, or any other operational constraints.

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?

It is a single front-loaded sentence with no redundant text. The brevity is efficient, though it leaves important detail unspecified.

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 return values need not be described. However, with no annotations and no parameter descriptions, the definition is missing too much needed context for correct invocation, especially around filtering and lookahead 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 description coverage is 0%, and the description does not mention any of the three parameters (as_of, event_types, lookahead_days). The parameter names alone do not fully convey accepted formats or filtering 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?

The description names a specific verb and resource ('List ... upcoming catalysts'), so the basic operation is clear. It does not explain how it differs from sibling tools such as event_readiness or assess_event.

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 guidance on when to use this tool versus alternatives, nor any exclusions or prerequisites. The listing intent is implied by the name and description, but the agent must infer the usage context.

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