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

Adds a lot beyond the read-only/idempotent annotations: OCR runs on Conecto's own server, OCR may misread digits so check says which pages to verify with documents_page_images, nothing is charged when no statement line is found, costs $0.05 per call with no charge on failure. These are pricing, accuracy-risk and verification details an agent cannot get 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?

Purpose and scope are front-loaded and every clause carries information (jurisdictions, source routing, OCR caveat, pricing). It is dense and runs long with parenthetical asides, which slightly hurts scannability but no sentence is filler.

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 does the work of explaining returns: each recognised line with its figures per year, page number, and the same field names companies_financials uses, scaled by the reported unit. The remaining gap is the unexplained page-range parameters, which leaves an agent guessing how first_page/last_page affect the read.

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%: file_id is documented, but first_page and last_page have no description in the schema or in the description text. The description never says what page bounds do or why you would set them, so it fails to compensate for the coverage gap on two of three parameters.

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 precise verb and resource: reads the balance sheet and income statement out of an annual report PDF, covering German HGB, English IFRS and UK GAAP. It distinguishes itself from neighbouring tools by referencing companies_financials fields, companies_save_accounts and documents_page_images, so an agent can identify the exact tool without opening 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 concrete routing context: for companies whose register publishes no figures, German ones come from their own report and big UK ones from accounts saved via companies_save_accounts, implying companies_financials handles the register-backed case. It doesn't spell out an explicit 'do not use this when...' rule or the relationship to documents_read_pdf, but the context is clear enough to select correctly.

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