Skip to main content
Glama

deep_search

Read-onlyIdempotent

Try multiple query variants in priority order until one returns strong results. Use when a single search fails or a more thorough search is needed.

Instructions

Multi-query fallback search. ESCALATION TOOL — use only when search returned weak or empty results, or when the user explicitly asks for a more thorough search. Slower than search because it runs multiple retrievals. How it works: tries each query variant in order; stops at the first whose results pass the weakness threshold. If all fail, returns the strongest weak set with a warning. Omit source to run across ALL sources (RRF-fused); pass source to target one. Configured sources: . Best practices: provide 2-4 GENUINELY DIFFERENT phrasings (different angles, not paraphrases). Good: ['player health system', 'damage and healing logic', 'HP component lifecycle']. Bad: ['player health', 'health of the player'] (too similar). Args: queries (ordered list of variants); source (optional name); top_k; mode ('dense'|'sparse'|'hybrid', single-source only); file_glob, extensions, path_contains; min_score, min_results (threshold overrides); return_all_variants (per-variant diagnostics, single-source only).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoRetrieval mode override (single-source only): 'dense', 'sparse', or 'hybrid'. Defaults to the server's configured mode.
top_kNoMaximum number of results to return. Defaults to the configured value.
sourceNoSource name from `list_sources`. Omit to use the default: all sources for `search`/`deep_search` (RRF-fused), or the single applicable source for the others.
queriesYes2-4 genuinely different phrasings of the same need (different angles, not paraphrases), tried in priority order.
file_globNofnmatch glob to restrict results by path/filename, e.g. `*.cs` or `**/Editor/*`.
min_scoreNoOverride the weakness threshold: a variant's results must beat this score to count as strong.
extensionsNoRestrict results to these file extensions, e.g. `['.cs', '.shader']`.
min_resultsNoOverride the minimum number of results a variant must return to be considered strong.
path_containsNoKeep only results whose file path contains this substring.
return_all_variantsNoIf true, include per-variant diagnostics in the response (single-source only).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

Annotations already indicate read-only and idempotent behavior. Description adds detailed execution flow: ordered trial of query variants, threshold-based stopping, and fallback to strongest weak set with warning. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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

Single dense paragraph front-loaded with purpose and escalation note, followed by mechanism, best practices, and a compact arg summary. Every sentence earns its place without redundancy.

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?

Given 10 parameters and output schema existence, the description covers all critical aspects: main behavior, parameter details, edge cases (weakness threshold, warning), and source targeting. No gaps.

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

Parameters5/5

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

Despite 100% schema coverage, the description adds significant value: explains `queries` with best practices and examples, clarifies `source` behavior (omission = all sources RRF-fused), and notes single-source restrictions for `mode` and `return_all_variants`.

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?

The description clearly states 'Multi-query fallback search' and immediately distinguishes from sibling `search` by labeling it an 'ESCALATION TOOL' with explicit when-to-use instructions.

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?

Description provides explicit when-to-use ('only when `search` returned weak or empty results'), when-not-to-use (slower than `search`), and best practices for constructing queries with concrete good/bad examples.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/lorenzo-cambiaghi/LynxMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server