Fix ABAP automatically (deterministic)

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

Even with readOnlyHint/idempotentHint annotations present, the description adds substantial behavioral context: fixes are applied in "verified batches" where each batch is re-parsed and any parse-breaking batch is discarded, so "the output is parser-guaranteed, never guessed". It discloses that unfixed findings surface in `remaining`, and that it "does not invent rewrites (only fixes abaplint defines)". The pure-function framing (source in → corrected code out) is consistent with readOnlyHint=true, so there is no contradiction.

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?

The description is long but every sentence earns its place: core action first, then the verification mechanism, the unfixed-findings contract, when to use, what it does not do with named alternatives, and a working example. There is no redundancy or filler; the structure flows logically from what → how → when → when-not → example.

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?

Given an output schema exists, the description need not document return values, yet it still pre-announces the `remaining` field. It covers scope (files, up to 32 per call via schema), the correctness guarantee, exclusions, sibling routing, and an example — complete for a 4-parameter tool with nested objects and two enums. 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 baseline is 3. The description adds value beyond the schema by giving a concrete invocation example ("fix_abap({ "files": [ { "source": ... } ] })") and by illustrating fix categories (keyword casing, MOVE → =) that help an agent anticipate what the `files`/`rules` parameters will produce. It does not elaborate on preset/abapVersion semantics, but the schema already documents those fully.

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 verb and resource — "Apply abaplint's own machine-applicable corrections to ABAP sources and return the corrected code" — and names the mechanism (deterministic, batched abaplint fixes). It explicitly distinguishes from siblings: "is not a formatter (format_abap pretty-prints without changing statements)" and points cloud-blocker work to plan_cloud_migration. An agent can tell exactly what this tool does and what it is not.

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?

Explicit when-to-use guidance: "Use this when someone highlights code and wants it corrected to best practices / modern syntax instantly, as the mechanical first pass before any AI rewriting, or to modernize a file before review." It also gives when-not-to-use with named alternatives — cloud blockers needing re-architecture go to plan_cloud_migration, and formatting goes to format_abap. Nothing is left to inference.

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