Search Entries

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: auto-merging of team DB results when TEAM_DB_PATH is configured, word-boundary matching, and how the mode heuristic behaves. It stops short of describing result ordering/pagination behavior, but it meaningfully reduces uncertainty.

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?

Five compact sentences with the core purpose first, then advanced usage, then syntax quirks — front-loaded and mostly waste-free. The GitHub-filter sentence is thin enough that it borders on filler, but nothing is redundant.

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?

Given 25 parameters and a modest 52% coverage, plus an output schema that removes the need to explain return values, the description covers the high-risk ambiguities (mode choice, FTS syntax, workspace/team merging) but leaves pagination, default filters, and half the filter parameters to the schema alone. Adequate but not complete for a tool this broad.

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 only 52% across 25 parameters, so the description must carry weight. It does explain mode semantics, sort_by, and the FTS5 query syntax (exact phrase, prefix*, boolean operators), which is genuinely useful. But it says nothing about limit, cursor pagination, tag filtering, include_team, include_archived, or the GitHub filter fields, so roughly half the surface remains undocumented.

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 ('Search journal entries') and enumerates the search modes (auto/fts/semantic/hybrid) plus the filter domain (GitHub Projects, Issues, PRs, Actions). It's clear what the tool does, though it never explicitly distinguishes itself from close siblings like semantic_search, search_by_date_range, or team_search.

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?

It gives one concrete usage cue ('Use sort_by: "importance" ... before major decisions') and explains the mode options, but gives no when-not guidance and no routing to alternatives such as semantic_search (semantic-only), search_by_date_range, get_recent_entries, or team_search. An agent still has to infer which sibling to pick.

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