Skip to main content
Glama
U-C4N

Thunderbird MCP

by U-C4N

Search everything

search_global
Read-onlyIdempotent

Ranked full-corpus search across every indexed folder and account.

Instructions

Ranked full-corpus search across every indexed folder and account.

Best for open questions — "what did we agree about the shipment", "anything from the accountant about VAT". Results carry a relevance score and a conversation id you can pass to search_conversation. For precise filters (one folder, unread only, a date range) use mail_search instead.

If this returns nothing unexpectedly, call search_index_status: the global indexer can be disabled or still catching up.

matched is how many of the retrieved messages matched, and it is the total only when truncated is absent; a truncated search ranked as deep as it could and there may be more below. unmatchableTerms names words the index cannot look up at all — anything that breaks into pieces of fewer than three characters, like "2.0" — and because every term has to match, one of those is enough to empty the result.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo
queryYes
offsetNo
folder_idNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), but the description adds genuinely non-obvious behavior: the global indexer can be disabled or lagging, and terms breaking into sub-3-character pieces are unmatchable, which can empty a result. It also explains that results carry a relevance score and a conversation id usable with `search_conversation`. Strong added context 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose and the routing decision, then layered detail. Every paragraph is substantive, though the final paragraph on `matched`/`truncated`/`unmatchableTerms` is dense and reads more like field documentation than selection guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-param search tool with an output schema, the description covers the selection decision, the alternative, failure diagnostics, and result-field interpretation. The only omission (limit/offset/folder_id semantics) is a parameter-level gap rather than a missing usage context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate, and it only partly does: it explains query-side semantics (matched/truncated/unmatchableTerms effects) but never describes `limit`, `offset`, or `folder_id` behavior or defaults. Pagination and folder scoping remain undocumented in both schema and description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Ranked full-corpus search') plus the scope ('across every indexed folder and account'). It explicitly distinguishes itself from the sibling `mail_search` by naming it and the condition that selects it, so an agent can route without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete when-to-use phrasing with example queries ('what did we agree about the shipment'), an explicit alternative for the opposite case ('For precise filters... use mail_search instead'), and a diagnostic fallback (`search_index_status`) for unexpected empty results. Nothing is left to inference.

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