explain_error

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

Annotations only supply readOnlyHint=true, and the description adds real behavior the annotation cannot: retry finality semantics ('a forbidden repeats on retry; fix the approach, not the request') and provenance ('parsed from the installed API reference, so codes match the SDK version the app runs'). Those are the two things an agent actually needs to decide its next action after a failure.

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-loaded with the trigger in the first clause and every sentence carries information (trigger, returned content, retry semantics, provenance, no-arg mode). The em-dash and parenthetical nesting makes it slightly dense to scan, but there is no wasted sentence.

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?

No output schema exists, and the description does tell the agent what comes back (meaning of the code plus the exact next step) and how to enumerate all codes. Minor gaps remain: behavior for an unrecognized code string and the shape/verbosity of the explanation are not stated, and annotations carry only the read-only hint.

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?

Only one parameter and schema description coverage is 100%, so the baseline is 3. The description goes beyond the schema by naming concrete code values (conflict, forbidden, unknown_collection, invalid_shape, html_not_allowed) and by clarifying that omitting the code lists every *stable* code, adding a nuance the schema's 'list all' does not.

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 (explain) and resource (GemmeinError code from a GemmeinError object), with the exact trigger condition 'the moment a GemmeinError reaches you'. That scope cleanly separates it from the sibling explainers (explain_rule, explain_relay) and the doc-lookup tools (guide, reference, search_docs).

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 an explicit trigger ('the moment a GemmeinError reaches you') plus a second invocation mode ('call with no code to list every stable code'), which is exactly the alternative an agent needs. It stops short of a when-not-to-use or explicit routing away from sibling explain tools, so it is clear context without full exclusion guidance.

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