epost_letter_text

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

With no annotations, the description carries the full burden and does a lot of it well: it discloses the return format (OCR layer laid out like `pdftotext -layout`), the runtime dependency (pdftotext/poppler), that `location` reports where the letter was found, plus a prompt-injection warning and an OCR-accuracy caveat. It does not state authentication/permission requirements or any rate limits, so it falls short of a 5.

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 purpose in the first clause, followed by return format, then safety caveats, then the dependency note. Dense but each sentence adds a distinct fact; the injection-safety and IBAN warnings are slightly expans. Still largely waste-free.

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 or annotations exist, so the description must explain the return shape, which it does (OCR layout text plus a location field), and it flags environment requirements. The main gap is the lack of letter_id format detail and no auth context, but for a simple read-text tool this is close to complete.

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 50%: max_chars is fully documented in the schema, but letter_id has no schema description. The description only says 'by letter_id' without format/expected-value guidance, so it does not meaningfully compensate for the undocumented required parameter. Baseline 3 for partial coverage.

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+resource+scope: returns the OCR text of one letter, found either in the inbox or in Storage, addressed by letter_id. It separates itself from download-style siblings with 'so a letter can be read without saving it anywhere', but it never names the closest siblings (epost_get_letter, epost_letter_pdf) to make the boundary 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?

Usage is implied ('read without saving it anywhere') rather than stated as a when-to-use rule, and there is no when-not or alternative named. An agent can infer this is the read-text-in-place option, but must compare against epost_get_letter and epost_letter_pdf by itself.

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