diana_experience_list

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered and the description only needs to add surface behavior. It does add useful detail: ordering is newest-first, listing returns id/title/status/type, and the response includes per-status counts plus files that fail to parse or are uncommitted. It says nothing about pagination limits or how large result sets behave, so the behavioral disclosure is helpful but not deep.

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 two-mode distinction, then a compact Args block, so an agent can scan it quickly. Minor waste comes from re-listing enum values already in the schema and from an untranslated term ('未验证') that sits oddly next to 'draft'.

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?

An output schema exists, so return values need not be described, and the description covers both invocation modes and every filter. Remaining gaps are modest: no default or maximum for limit, no statement about whether id short-circuits other filters, and no indication of how the parse/commit warnings should be interpreted.

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 0% across 7 parameters, so the description has to carry the load, and it does define each argument's intent — including what fields query matches (title, triggers, tags, text) and what details adds (tags, triggers, source, date, usage). However, limit is only glossed as 'number of entries' with no default (30) or ceiling, and the status/type value lists largely restate enums already visible in the 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?

The description states a specific verb and resource ('Browse the experience handbook, or read one entry in full') and clearly splits the tool into two modes keyed on the id argument. It is easy to separate from write-side siblings like diana_experience_add/update/verify, though it never explicitly names a read-alternative (e.g. diana_knowledge_search) to disambiguate against.

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?

Mode selection is spelled out: 'Without id' produces a filtered list, and supplying id reads one entry in full. It also explains that status=draft is effectively 'the review queue of 未验证 entries', which is real operational guidance. It stops short of stating exclusions, e.g. whether id overrides the other filters or when to prefer a sibling search tool.

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