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

Annotations only give the generic safety profile (readOnlyHint=false, destructiveHint=false, non-idempotent), while the description adds real operational context: the file must be transmitted byte-for-byte unmodified, #PROGRAM and #ORGNR lines must survive, and the ingestion fills company, fiscal year, income/balance statements, notes and periodiseringsfonder using the same code path as manual upload. It also states the return ('snapshot efter inläsningen'), which no output schema covers.

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, then transport guidance, then prerequisites/workflow. The 'skriv aldrig av eller redigera filen' warning is repeated in the description and again in the content_text schema field, which is mild redundancy, but every paragraph otherwise carries unique information.

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 five-parameter, state-dependent ingestion tool with no output schema, the description covers transport method, size limits, encoding, prerequisite draft state, side effects on draft data, and the return value. Nothing an agent needs in order to invoke it 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 the baseline is 3, but the description adds selection logic the schema does not: upload_id is recommended for files over ~30 kB, content_text only when the user pasted the text themselves, and content_base64 preserves the character encoding. That is genuine decision support beyond the field 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?

States a specific verb and resource ('Laddar upp en SIE-fil (SIE4) till utkastet och läser in den i steg 1') and explicitly contrasts itself with the sibling create_sie_upload, which only stages the file. An agent can distinguish it from create_sie_upload and read_draft 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?

Gives an explicit preferred path (create_sie_upload → curl --upload-file → upload_sie with upload_id) plus a fallback (content_base64 for small files), and names the prerequisite state (draft open in AI mode, on step 1, otherwise go_to_step 1). It also routes the next actions (get company data, press_button, next_step), so the agent knows both when to call it and what to do after.

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