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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the description only needs additive context. It contributes one useful behavioral detail: with session_id each group gains a 'why' field explaining relevance, which matters since there is no output schema. It says nothing about coverage gaps, limits, or what happens when parameters are insufficient.

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?

One front-loaded sentence covering the purpose, both input modes, and the conditional output difference, with zero filler. The nested parentheticals make it slightly dense to parse on first read but nothing is wasted.

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?

With no output schema, the description carries the return-value burden and does so at a high level (grouped materials, plus 'why' in diagnostic mode). The remaining gap is the zero-required-params situation: it never says what happens with only domain, only level, or no parameters at all.

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 baseline is 3, but the description adds genuine relational meaning: domain+level form one selection path, session_id is an alternative path that additionally changes the response shape. That combination logic is not encoded anywhere in the flat 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?

States a specific verb+resource — recommendations of development materials for a competency — and distinguishes two selection modes (domain+level versus session_id). It falls just short of a 5 because it never explicitly contrasts itself with the sibling ruforge_kb_search, only referencing it as a source of slug format.

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 clear context for each mode: use domain+level when you know the competency and current level, use session_id when you want results grounded in a completed diagnostic. It does not state when-not to use it (e.g. plain article lookup belongs in ruforge_kb_search), so exclusions are implied by the sibling list rather than written.

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