ts_discover

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is largely covered; the description still adds the 'PII-safe' guarantee and the default scan scope over ~/.claude/projects/, which are not derivable from the annotations. It does not describe cost, runtime, or volume of a full scan, so it is not a full 5.

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?

Three dense sentences: purpose first, then scope/default behavior, then the format-mode semantics, closing with the safety note. No filler and no repetition, and the most decision-relevant information (what it scans, how to filter, which format does what) is front-loaded.

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 and zero required parameters, the description carries the return-value burden and does so: it explains that table/json yield ranked Findings and adoption modes yield a summary with trend and worst sessions. Combined with annotations covering safety, an agent has everything needed to call it correctly.

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% and every parameter is already documented in the schema, so the baseline is 3. The description restates the format modes and project filter but adds no syntax or semantics beyond what the schema provides (e.g., no guidance on since_days interaction with the adoption mode).

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 ('Scan Claude Code transcripts for missed Token Savior opportunities... report TS-vs-native adoption ratios') with enough detail to distinguish it from ts_search, ts_execute, and ts_stale_context, which are the nearest siblings. The parenthetical explaining 'native-call chains that should have been a single TS call' makes the intent 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?

Clearly frames the two use cases (missed-opportunity findings vs. adoption reporting) and maps each to a format value, and it states the default scope plus how to narrow it with project=<substring>. It does not explicitly name a sibling to prefer instead or state when-not to use it, so it falls short of a full 5.

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