SAPRead

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

Annotations declare readOnlyHint=true, which the description confirms as a read operation. Beyond that, the description adds substantial behavioral context: token-saving strategies (method='*' ~95% fewer tokens), grep's case-insensitive regex behavior with context lines, version semantics (active vs inactive draft vs auto), the note that active reads flag pending drafts, and cost notes on structured format (+10% to +1685%). It also discloses on-prem-only types. Does not contradict annotations.

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 dense and information-rich but quite long — a single dense paragraph covering type distinctions, usage heuristics, and behavioral details. It front-loads the core purpose and primary use guidance before diving into per-type detail. While every sentence carries value, the wall-of-text structure makes key guidance (e.g., 'prefer SAPContext first') less scannable than it could be with light structuring.

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?

A few sentences are sufficient to describe a read-only source accessor that returns a status entity. The description must convey read-only nature (a direct declaration), the source of truth field, the timestamp, and usage context (when to call it). The GET verb is implicit in the tool name and operation, so minimal elaboration is acceptable. For such a simple tool the description is appropriately brief while covering the essential semantics.

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 schema already documents all 23 parameters in detail. The description adds value by cross-referencing parameter combinations (e.g., where= for TABLE_QUERY with AND semantics, include= for CLAS local files vs DDLS elements vs VERSIONS history, expand_includes recursively expanding LZ<grp>U01/U02 includes). It clarifies subtle interactions like not combining grep with method=, and from/to semantics for diff. The description enriches rather than repeats the schema.

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 opens with a specific verb+resource: 'Read SAP ABAP objects' with exhaustive detail on what raw source, method body, grep output, inactive drafts, revision history, or metadata can be fetched. It explicitly distinguishes from the sibling SAPContext ('prefer SAPContext first') and enumerates 30+ object types, making both purpose and scope unmistakable.

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?

The description gives explicit when-to-use guidance ('prefer SAPContext first for intent-level context before raw source') and names the alternative tool. It provides concrete usage heuristics like preferring method= for token savings, when to use grep vs method, when to use structured format, and per-type clarifications (TABL covers structures, expand_includes for FUGR). Clear do/don't guidance throughout.

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