bw_get_afo_workbook

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

No annotations exist, so the description carries the full burden and does so richly: it discloses non-locking behavior, that BW enforces the caller's authorization, the local-server constraint on save_path, base64 payload size implications, and the exact failure mode when SOAP RFC is inactive ('the answer says so when it is not'). It also enumerates return contents, compensating for the absent output schema.

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-loads the core purpose and return set, then the two output modes, then prerequisites. Sentences are dense but each carries distinct information (locking, auth, service dependency). Slightly packed with multiple ideas per sentence, but no 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?

For a 4-param, no-annotation, no-output-schema read tool, the description covers what it returns, side effects (disk write, no lock), authorization, and the infrastructure dependency and its error surfacing. Nothing an agent needs to call 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 description coverage is 100%, so the schema already documents name, overwrite, save_path (directory/slash/extension resolution, local-only) and include_content (4/3 size, default false). The description's parameter mentions largely restate the schema (save_path local-only, include_content base64) rather than adding new syntax or precedence rules. Baseline 3 is warranted.

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 (fetch one Analysis for Office workbook in BW) and immediately signals the read-only semantics ('as AFO opens it, without locking it'). It distinguishes itself from siblings by referencing bw_list_afo_workbooks for the where-used/role-menu shape and implying the contrast with bw_save_afo_workbook. An agent can tell which workbook tool to pick without opening a 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 when-to-use context (fetch a single workbook without locking, save it to disk locally, or get base64 content) and operational prerequisites (server must run locally for save_path; SOAP RFC service must be active). It names the sibling bw_list_afo_workbooks for the listing case, but does not explicitly say 'use list to discover names, then this to fetch' or exclude other alternatives. Strong but not fully explicit routing.

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