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

With annotations already covering read-only/idempotent safety, the description adds substantial domain context: the 180-day consent ceiling, the four possible state values, and a privacy constraint ('Show the result only to the account owner'). None of that is recoverable from the structured fields.

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?

Four short lines, front-loaded with purpose before the exclusions and the privacy note. The line-broken fragment style is slightly choppy, but no sentence is wasted.

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-value documentation is unnecessary, yet the description still enumerates the state values an agent must branch on. Combined with the scope limits and privacy rule, nothing needed to call this 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 coverage is 100%, so both `remote` and `warn_days` are fully documented in the schema. The description nods at the warning concept but adds no format, unit, or interaction detail beyond what the schema already states; 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?

Opens with a specific verb+resource+return: 'Read-only consent expiry: valid until, days left, and a warning.' It is immediately distinguishable from siblings like get_balances or get_transactions, which deal with money rather than consent state.

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 bounds usage: 'This does not renew the consent and cannot move money. Renew with `n26-eb connect`.' It names the alternative tool for the adjacent task an agent might confuse this with, which is exactly the routing guidance needed.

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?

Beyond the annotations (readOnlyHint), it provides crucial behavioral context regarding data fields returned (type, amount, currency, date) and a necessary authorization constraint (only shown to the account owner).

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 brief and front-loaded, though the second sentence slightly over-explains the basic data structure that is often inferred from an output schema.

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?

It is extremely complete for a read-only, scoped query. It defines the boundaries (consented accounts), the scope of the result (owner only), and the data included (fields).

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?

Since schema coverage is 100%, the description adds value by reinforcing the meaning of the 'account' parameter—that omitting it retrieves balances for all consented accounts, which is the core functionality.

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 clearly identifies the resource (balances) and the action (read-only), distinguishing it from siblings like list_accounts by specifying the operational scope.

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 guides usage by explaining that the results are tied to consented accounts, and explicitly notes that no payment action is possible, helping the agent avoid misuse.

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 read-only, idempotent and non-destructive, and the description still adds substantial behavior: it transparently discloses internal continuation-page traversal, that only the newest matching rows are returned, the context-protection cap (default 50, max 200), the sign convention (debits negative, direction DBIT), the absence of any payment action, and a privacy constraint ('show the result only to the account owner'). These are non-obvious traits an agent could not infer from structured fields.

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 core purpose, then progressive detail on paging, filtering, alternatives and constraints. Every sentence carries actionable information; nothing is filler, and the only repetition (50/200 cap) is restated to justify the context-safety rationale.

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 six-parameter, open-world read tool with an output schema, the description covers everything an agent needs: paging behavior, truncation limits, filtering strategy, alternatives, sign conventions and a privacy caution. Return-value structure is correctly left to the output schema.

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%, so the baseline is 3, but the description adds rationale the schema lacks: why the limit exists (so a long history does not fill context) and that narrowing dates or searching is preferable to raising it. It does not add syntax or format detail beyond the schema, so it stops short of 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 and resource plus scope: 'Read-only transactions for a date range.' It also clarifies the retrieval model (follows Enable Banking continuation pages, then returns newest matching rows) and names the sibling tools to use for a different job, so an agent can separate it from recurring_charges without opening any 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?

Explicit routing guidance: 'Filter with search, or narrow date_from and date_to' and 'For a summary, use recurring_charges or the monthly spending resource instead of raising the limit.' It gives both the positive usage pattern and the when-not/alternative, which is exactly the decision an agent faces.

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, closed-world and non-destructive, so the description adds real value by disclosing that it reads a local session file rather than calling the bank (implying possible staleness) and that it cannot move money. The data-handling restriction is a genuine operational constraint not encoded anywhere in the structured fields.

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 short sentences, front-loaded with the read-only/consent scope, then behavior, then the disclosure rule. No filler, and the most decision-relevant fact comes first.

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 zero parameters, rich annotations and an output schema, the description covers the remaining gaps: data source (local session file), non-network behavior, and the privacy constraint on displaying results. Only the freshness/refresh semantics of the session file are left implicit.

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, which is the baseline-4 case; there is nothing for the description to disambiguate. The return-field sentence compensates usefully by describing what the caller gets back.

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 ('read-only list of accounts') plus its scope ('covered by the current bank consent'), and enumerates the returned fields. It is clearly distinct from get_balances/get_transactions by resource, though it never names those siblings to route the agent 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 implied by the consent-scoped framing, and the disclosure instruction ('show the result only to the account owner') tells the agent how to present output. There is no explicit when-to-use/when-not guidance or comparison to the sibling read tools, so the agent must infer selection.

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 openWorld, so the safety profile is covered. The description adds genuinely new behavior: pagination is handled internally, overdue series are marked 'lapsed?', and results are restricted to the account owner — none of which the annotations 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?

The core purpose is front-loaded in the first sentence, followed by output shape and constraints. Slightly terse shorthand ('lapsed?') costs a little clarity, but there is no wasted text.

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 needn't be re-explained; the description covers what structured fields don't — internal pagination, the no-payment guarantee, and the owner-only disclosure rule. For a read-only detector with full schema coverage, an agent has everything needed to call and present 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 100%, and every parameter (today, account, date_to, date_from, min_count, include_credits) is already documented in the schema, including the 'six to twelve months works well' hint and the quarterly/yearly min-count exception. The description adds no parameter-level meaning beyond that, so the 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?

States a specific verb and resource — 'Read-only detection of subscriptions and other recurring charges' — which is clearly distinct from the sibling list/balance/transaction tools. It also names the underlying detector ('Same detector as `eb.py recurring`') and enumerates the derived outputs, so an agent knows exactly what this produces.

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 tool detects recurring series, so an agent infers raw transaction listing belongs to get_transactions, but no sibling is named and no explicit 'use this instead of X when Y' guidance is given. It does include one useful exclusion ('There is no payment action') and a handling rule ('Show the result only to the account owner'), which lifts it above pure absence of guidance.

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