List Runtime Errors (ST22)

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the bar is lower, but the description adds substantial behavioral context beyond that: the server returns a fixed page regardless of max_items, user filtering and max_items are applied to that page locally, and housekeeping jobs eventually remove old dumps. This is exactly the kind of non-obvious behavior an agent needs to know before calling.

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 organized into Args, Returns, Examples, and Notes, with the core purpose stated first. Every section adds distinct value: format defaults, return shape, concrete examples, and important behavioral caveats. It is longer than average but avoids redundancy and front-loads the most actionable details.

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?

Even though there is no output schema, the description fully specifies the return JSON shape with field names and optional markers. It also covers pagination behavior, data retention, date format, default/max values, and how to chain into sap_get_dump. An agent has everything needed to decide when to call it and how to interpret the results.

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% for all five parameters, so the schema already documents formats and defaults. The description adds meaningful semantics on top: it clarifies that from_date/to_date are server-side filters while max_items and user are applied to the returned page, and that the URI may contain encoded characters and should be passed verbatim. This goes beyond what the schema descriptions state.

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?

Describes the exact operation: listing recent ABAP runtime errors (ST22 short dumps), including the fields returned (error ID, program, user, time, and URI). The title and description align, and the resource is unambiguous. It also distinguishes itself from sap_get_dump by pointing out that the URI is meant to be passed to that sibling tool, so an agent can tell listing from fetching.

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?

Provides clear usage context: examples show when to use date filters, max_items, and user filtering. The Notes explicitly explain that from_date/to_date are the only server-side filters and that max_items/user filtering happen client-side, which clarifies when to use which parameter. It doesn't explicitly say 'use sap_get_dump instead when you have a URI', but the return-URI note strongly implies the workflow.

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