KB Session Recap

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint. Description adds the format of the summary (N committed, M demoted-to-pending, K rejected) and references the feedback loop context, which adds useful behavioral insight beyond 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?

Two sentences, clear and front-loaded with the summary. The issue reference (#112) adds minor noise but doesn't harm clarity. Could be slightly more concise, but overall 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?

With high schema coverage, annotations, and an output schema (present), the description provides sufficient context for a simple parameter tool. It explains the purpose and usage scenario adequately without needing to detail returns.

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 covers the one parameter (source_session) fully. Description doesn't add extra semantics but restates it implicitly by context. Baseline 3 is appropriate as schema does the work.

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?

Description clearly states 'Read-only per-session write summary' and lists the counted categories (committed, demoted-to-pending, rejected). It distinguishes from sibling `kb_pending` and implies a specific scope per session, making the tool's purpose unambiguous.

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?

Explicitly states when to call: 'whenever a write response indicated a demotion, to confirm the current tally before informing the operator.' Also names an alternative (`kb pending`) and provides a specific context (issue #112 feedback loop).

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