Skip to main content
Glama
This connector has been deprecated

Server capabilities and search pitfalls

shamela_brief
Read-onlyIdempotent

بيان قدرات الخادم ومزالق البحث

Capability handshake + operating brief for programmatic callers. Call this FIRST, before sending any argument you are not certain this build accepts. Returns capabilities[] — the arguments and response fields this server supports — plus server_version, limits, and traps[]. Every tool input here is strict, so sending an unknown argument (e.g. shape, response_format:'none') to a server that predates it is a HARD validation error that fails the whole call, not a silently ignored field; and tools/list cannot help, because it proves a tool exists without saying which arguments it takes. Gate each new argument on its capability string. traps[] is the operating half: each entry pairs a way a search result misleads with the exact RESPONSE FIELD that proves it fired (relaxed_min_match, zero_hit_terms, paging_ceiling, coverage.sample_is_complete, scope_resolution.dropped, madhab_source, probes[].qualifiers, …), so a caller checks the envelope instead of trusting prose. brief_hash covers every other field: cache the brief and re-fetch only when it changes. Pure text and constants — no library access, so it answers even when the Shamela install is missing. Examples: shamela_brief({}), shamela_brief({response_format:'json'}).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
response_formatNoOutput format for the human-readable text. 'markdown' (default) is best for direct display; 'json' returns the same data as a single JSON code block; 'none' skips the rendered text entirely and returns a one-line pointer, leaving `structuredContent` as the whole answer. The structured data is returned in `structuredContent` regardless of this setting, so a caller that parses it should pass 'none' — the character budget is measured over BOTH channels, and the unread copy is otherwise spending most of it. Requires the 'response_format.none' capability (see shamela_brief).markdown

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
trapsNo
limitsNo
truncatedNo
brief_hashNo
capabilitiesNo
rows_droppedNo
server_versionNo
truncation_messageNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial behavioral context beyond them: strict validation makes unknown arguments a hard failure (not silently ignored), the brief works even without the Shamela install, brief_hash supports caching, and traps[] pairs failure modes with the exact response field that proves them. This is rich disclosure that the annotations alone do not convey.

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?

Dense and front-loaded — the purpose and 'call first' instruction lead, followed by return contract, validation caveat, traps explanation, and caching. It is long, but nearly every sentence carries distinct operational information; a modest trim would still improve it.

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?

An output schema exists, so return values need no prose, yet the description still enumerates the key returned fields (capabilities, server_version, limits, traps, brief_hash). For a 1-param meta tool this is fully complete.

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

Parameters4/5

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

With only one parameter and 100% schema coverage, the schema already carries the semantics; baseline is 3. The description adds value by clarifying the response_format examples and tying 'none' to the capability gate, but most parameter detail lives in the schema.

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 function: a capability handshake and operating brief that returns capabilities[], server_version, limits, and traps[]. It is unmistakably a meta/discovery tool, clearly distinguished from all the shamela_get_*/shamela_search_* siblings that do actual retrieval.

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?

Explicit sequencing instruction: 'Call this FIRST, before sending any argument you are not certain this build accepts.' It also gives the negative case (gate each new argument on its capability string) and explains why tools/list cannot substitute. 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.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources