COLA Insight

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and a closed world, so the safety profile is covered. The description adds one genuinely useful behavioral fact — that the output is an educational estimate with no official SSA authority — but says nothing about calculation assumptions, rounding, or how a missing Part B premium is handled.

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 tightly written sentences with zero padding; the core action is front-loaded and the caveat follows directly. Every clause earns its place.

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, and the description partially compensates by naming the two returned quantities (monthly and annual change). But with two undocumented parameters and an unstated calculation basis, an agent still lacks enough to invoke this confidently beyond the single required field.

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% for two parameters, so the description carries the burden and largely fails it. 'Monthly benefit change' loosely implies currentMonthlyBenefit is a monthly dollar figure, but medicarePartBPremium is never mentioned, and no units, formats, or bounds are given for either input.

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 action (estimate monthly and annual benefit change) and the data source (COLA Insight's latest tracked rate), so an agent can tell this is a computation rather than a data-fetch like the get_cola_* siblings. It stops short of explicitly contrasting itself with those siblings, but the verb+resource pairing is 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?

Usage is implied by the 'educational estimate' framing and the disclaimer that it is not an SSA determination, which hints at when the result is and isn't appropriate. However, it never says when to reach for this tool versus get_current_cola or get_cola_history, and no prerequisites (e.g. needing a current benefit amount) are stated.

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, closed-world behavior, so the safety profile is covered. The description adds genuinely useful behavioral context by disclosing that results come back in reverse chronological order, but says nothing about how many records exist, pagination, or what 'preserved' snapshots represent.

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 no filler, and the ordering information is front-loaded alongside what is returned. Nothing is wasted, though it is arguably too terse given the gaps elsewhere.

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 and no parameter documentation, the description does the minimum: it names the three snapshot types and the sort order. It leaves unresolved how many snapshots exist, what limit controls, and whether the list can be paged, which an agent would want before calling.

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 parameter (limit) with 0% schema description coverage, so the description carries the full burden and fails to compensate: it never mentions limit, its default of 10, its 50 maximum, or pagination behavior. Only the schema's numeric bounds hint at its meaning.

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 (Return) and resource (preserved COLA snapshots) and enumerates the three snapshot kinds returned. It is distinguishable from get_current_cola by the word 'history', though it never explicitly contrasts itself with that sibling.

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: the word 'history' versus the sibling get_current_cola suggests retrieving past snapshots rather than the live value, but the description states no when-to-use condition, prerequisites, or alternative. An agent must infer the routing.

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, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description adds only the content categories returned and says nothing about response format, permissions, or other behavioral traits.

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 with no wasted words. It immediately states the action and the resources returned.

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 zero-parameter, read-only metadata tool with rich annotations, the description tells the agent what data it yields. However, with no output schema, it does not explain the response structure, and it gives no usage context relative to 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?

The tool takes zero parameters, so there is nothing for the description to clarify. The baseline of 4 is appropriate.

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 ('Return') and four concrete content types (government sources, methodology, data dictionary, public datasets) scoped to COLA Insight. It is clear, but it never references the sibling tools (get_current_cola, get_cola_history, calculate_benefit_change) or explicitly distinguishes itself, so it falls short of 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 when-to-use guidance, no mention of alternatives, and no exclusions. The only implied usage is 'call this when you need provenance information,' which is too thin to count as 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 readOnly, idempotent, non-destructive, and closed-world behavior, so safety is covered. The description adds genuinely useful behavioral context by enumerating the returned fields (status, rate, CPI-W observations, timestamp, source links) and signalling that the data is 'tracked' for a specific period (2027), which is important since there is no output 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?

A single tightly written sentence with no filler, and the most important information (what is returned) is front-loaded. Nothing could be removed without losing signal.

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 input parameters and no output schema, the description carries the burden of describing the return payload, and it does so by listing the concrete fields returned plus their vintage. It is nearly complete; only the freshness/caching semantics of 'latest tracked' remain slightly ambiguous.

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 nothing for the description to clarify; the baseline for a parameterless tool is 4. No parameter-related information is missing or misleading.

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 specific verb ('Return') and resource ('latest tracked 2027 Social Security COLA status, rate, CPI-W observations, timestamp, and primary source links'), so the agent knows exactly what data comes back. It implicitly distinguishes itself from get_cola_history by saying 'latest' and 'current', but it never names the sibling tools explicitly.

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: 'latest' versus the sibling get_cola_history and get_cola_sources suggests this is the snapshot tool, but there is no explicit when-to-use, when-not-to-use, or named alternative. An agent can infer the routing, but the description does not state it.

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