Skip to main content
Glama

Send feedback to Ekaya

send_ekaya_feedback

Sends feedback about the Ekaya MCP server itself to the Ekaya team. Use it when one of this server's tools blocked you, failed in a way its answer did not explain, made you use a workaround, or lacked something you needed. Do not use it for problems in the user's data, questions for the user, or refusals that told you what to do next (for example a permission you can ask an Administrator for). Call list_ekaya_feedback first. If your problem is a listed known issue, pass only its feedback_id to add your vote. Otherwise describe the problem in your own words. Never include query results, row values, SQL, URLs, email addresses, credentials or anything copied from the user's data; the server refuses text that looks like any of these. Three rows with the same nonzero comma, tab, semicolon or pipe count are refused, including prose lists. Bearer followed by any word and credential type names followed by : or = and a value are refused too. A content refusal identifies the field and rule and, when available, a closed shape and inclusive 1-based source lines; rewrite those lines without quoting the refused content. A JSON range may cover only part of a nested structure, so rewrite the whole structure. The description may run to 10000 characters and 100 lines; any report within the stated bounds fits the request size Ekaya accepts. Tell the user what you sent; call list_ekaya_feedback later to see its status.

Input Schema

NameRequiredDescriptionDefault
titleNoOne line, printable characters, in your own words.
categoryNoblocker: cannot continue; workaround: had to work around it; request: a missing capability, nice-to-have, wishlist item or suggestion; comment: other feedback.
tool_nameNoMust name a tool registered on this server.
error_codeNoThe refusal code an Ekaya tool returned.
descriptionNoAt most 100 lines, in your own words. Never include customer data or credentials.
feedback_idNoThe id of a published known issue, or of one of your own reports (which answers already_voted). Any other id, including one removed after it was closed, answers feedback_not_found. Supply this alone to vote.

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?

Goes well past the annotations (readOnly=false, openWorld=true, idempotent=false, destructive=false) by disclosing the server-side content filter heuristics (row/separator counts, bearer-token and credential-assignment patterns), the shape of a content refusal (field, rule, optional closed shape, inclusive 1-based source lines), size ceilings (10000 chars / 100 lines), and the vote-path outcomes (`already_voted`, `feedback_not_found`). These are non-obvious behaviors an agent could not guess from structured fields.

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 correctly — purpose, then when/when-not, then procedure, then content constraints, then closing follow-up advice. It is dense and somewhat sprawling in the refusal-rules sentence (separator counts, bearer words, credential names with ':' or '='), but each clause encodes a hard constraint that prevents a rejected call, so little is truly wasted.

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 non-idempotent write tool with a branching schema, no output schema, and a content filter, the description covers selection, procedure, validation rules, failure interpretation, and post-call behavior (tell the user, re-check status later). No output schema exists, and the description compensates by describing refusal responses itself.

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?

Schema coverage is 100%, so the baseline is 3. The description still adds real meaning by explaining the oneOf fork in intent: `feedback_id` alone means 'vote on this issue', while the absence of it means 'write a new report in your own words' — a distinction the schema encodes structurally but does not motivate. It also warns that ids of removed/closed issues yield `feedback_not_found`.

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, resource and scope: 'Sends feedback about the Ekaya MCP server itself to the Ekaya team.' The 'about the server itself' qualifier immediately separates it from reporting problems in user data, and the sibling `list_ekaya_feedback` is named as the companion read tool.

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 explicit trigger conditions (blocked, unexplained failure, workaround, missing capability) and explicit exclusions (user data problems, questions for the user, refusals that already said what to do next), plus a procedural fork: call `list_ekaya_feedback` first, pass only `feedback_id` to vote on a known issue, otherwise write a new report. Nothing needed for tool selection 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