SAPManage

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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description aligns: it distinguishes read actions ('features', 'probe', 'cache_stats', flp_list_*) from mutating actions and notes that mutating ones 'require writable safety config and write scope in authenticated mode'. The description adds meaningful behavioral context beyond annotations: caching semantics ('fast, no round-trip'), returns (features + systemType), and the concrete directive that 'available: false means do NOT attempt dependent operations'. Slight deduction for not spelling out exactly what 'probe' validation entails in terms of side effects or cleanup.

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 but front-loaded with the most important purpose and usage guidance. The action list is well-structured with a clear read vs write grouping, and FLP methods are compactly enumerated. Minor deduction: the action enumeration overlaps heavily with the schema's action enum, and the set_api_state detail sentence is somewhat bulky, but overall every section earns its place and the prose is resource-efficient.

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?

This is a high-complexity tool (23 params, multiple sub-domains: probe/features, package lifecycle, FLP read and write, set_api_state). The description covers every domain, rules out ambiguities (deprecation, alternative LADI path), documents defaults and edge cases (contract support per object type), and states return values (features + systemType) since there's no output schema. Given the breadth and the strong schema coverage, the description is appropriately 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 description coverage is 100%, so the schema already documents all 23 parameters thoroughly with inline descriptions. The description adds a handful of meaningful semantics beyond the schema: the action list with read-vs-mutating classification, the set_api_state default values (RELEASED, C1, with C0 for SRVD and C3 for views) which clarify the apiState/contract params, and the write-scope gating requirement. However, most parameter semantics live in the schema, so the description doesn't carry the heavy lifting here — hence a baseline 3.

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 statement: 'Probe and report SAP system capabilities' and explicitly frames when to use it ('Use BEFORE operations that depend on optional features'). It clearly distinguishes from siblings by listing covered domains (abapGit, RAP/CDS, AMDP, HANA, UI5/Fiori, CTS transports, FLP) and package lifecycle. The action list with inline sub-descriptions clearly delineates the tool's many functions.

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 provides explicit usage context: 'Use BEFORE operations that depend on optional features' and lists specific features. It also gives exclusion guidance, e.g., 'Classic designer tile/target-mapping model, deprecated since S/4HANA 2023; Work Zone exposure v2 needs LADIs (SAPRead type=UIAD)' — directing to an alternative tool. The 'available: false means do NOT attempt dependent operations' instruction is a clear when-not-to-proceed signal.

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