DocFig

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds substantial context beyond them: no network upload, no API key, row-by-row running-balance walk, and a specific output claim ('reports rows ... each with a likely fix') plus parity with `docfig check --json`. Nothing here contradicts the annotations.

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 compact sentences: the purpose and error list come first, then the input contract and the CLI-equivalence note. Every clause carries information; nothing is 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 8 optional parameters and no output schema, the description carries the return-value burden itself by naming what the report contains (offending rows plus likely fixes) and by pinning down both input formats and offline behavior. An agent has everything needed to call 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 coverage is 100%, so the baseline is 3, but the description adds the either/or relationship between the two input parameters and reiterates that the first row is the header, which is the highest-risk mis-input. It does not clarify opening/closing_balance usage beyond what the schema already 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?

The description opens with a specific verb and resource ('Check a bank or credit card statement's transactions table for errors') and enumerates the exact defect classes it detects, so the agent knows precisely what the tool does. It never names the siblings (convert_statement, combine_statements) to differentiate, which keeps it just short of 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?

It gives concrete invocation context — 'Free and offline: no API key, nothing is uploaded' — and explains the two accepted input modes ('Give the table as csv_text ... or as rows'). However, it offers no when-not-to-use guidance or routing to the convert/combine siblings.

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?

Goes well beyond the annotations: it discloses the reconciliation logic (missing months, overlapping periods, duplicates kept once, non-carrying balances), the return payload (accounts, problems, counts, file links), the one-hour validity of the combined file, and that the user's DocFig API key is used. Annotations only say non-read-only, non-idempotent, open-world; the description supplies the operational detail an agent needs.

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, but front-loaded with the action and packed with useful clauses rather than filler. The parentheticals (gaps, kept once, valid one hour) are information-bearing, though splitting the return-value clause into its own sentence would improve scanability.

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?

No output schema exists, so the description's summary of the return payload and file expiry is essential and present; annotations cover the safety profile. The one notable gap is that zero parameters are required and the description never says at least one of files or statement_ids must be supplied, leaving an agent able to construct an empty call.

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 schema already documents file_url vs file_base64, passwords, wait_seconds and statement_ids. The description adds only the one-hour reuse window for statement_ids, which the schema states anyway, and omits the 12-file cap and 20 MB limits. Baseline 3 applies when the schema carries the weight.

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 ('Convert several statements ... and combine them into one set of accounts') plus the concrete processing it performs: gap detection, overlap handling, dedupe, balance carry-over. The plural 'several' and the reference to statement_ids from convert_statement distinguish it from the single-statement sibling without the agent needing 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?

Gives clear context for the two entry paths: fresh files, or reuse of statement_ids from convert_statement or a prior combine_statements call within the last hour. It does not explicitly state when to prefer convert_statement alone or check_transactions instead, so no exclusions are offered.

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 only declare the generic profile (readOnly=false, openWorld=true, destructive=false), while the description adds concrete behavior well beyond that: it consumes the user's API key and monthly page quota, masks account numbers, stores nothing, deletes results after one hour, and expires the download links. It also notes the password is used once in memory and never logged – exactly the kind of mutation-adjacent disclosure an agent needs.

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?

Everything is in one dense, front-loaded paragraph that leads with what the tool does, then inputs, then returns, then privacy/quota. The pricing-and-signup URL is slightly promotional but carries practical auth/quota information, so it roughly 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?

With no output schema, the description enumerates the return payload (bank, period, totals, check status, flagged rows, first N transactions, download links) and their one-hour lifetime. For a 7-parameter, open-world tool that is complete enough to call 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 coverage is 100%, so the baseline is 3, but the description adds real semantics: the choice between file_url and file_base64, and that statement_id is used 'instead of a file' to retrieve a still-converting job's result, which explains the wait_seconds polling loop. That is meaning beyond the field-level descriptions.

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?

A specific verb and resource ('convert a bank or credit card statement... into transactions') plus supported input formats and the balance-check behavior. It does not, however, distinguish itself from the sibling check_transactions, even though 'every row checked against the balances' overlaps with what that name implies.

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 does state the input alternatives ('Give file_url or file_base64', and statement_id to fetch an earlier result), which is genuine usage guidance. But it never says when to call this versus check_transactions or combine_statements, nor what prerequisites apply beyond needing a DocFig key.

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, openWorldHint and destructiveHint=false, so the safety profile is covered. The description contributes the quota context — that figures are per API key and reset periodically — but says nothing about the response shape or whether 'used' and 'left' are returned as a total or per-period.

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 sentence carries the whole definition, front-loading the metrics (pages used, pages left) before the reset detail. Nothing is padded, though the phrasing is slightly compressed.

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 hint at return values, and it does: pages used, pages remaining, and the reset time. For a zero-parameter, read-only quota check, this is nearly everything an agent needs to decide to call it.

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 the baseline of 4 applies. The description correctly signals that no inputs are required by framing the result as scoped to 'the DocFig API key'.

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 (pages used/left this month) and adds scope details — per DocFig API key and the reset timing — that the brief title alone does not. That makes it clearly distinct from the unrelated siblings (check_transactions, combine_statements, convert_statement).

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: an agent would call this to check remaining quota before hitting limits. However there is no explicit when-to-use statement, no mention of what to do when pages run out, and no named alternative — though none of the siblings are alternatives here.

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