Rate a search result you actually used. Call at the end of a task for the result(s) that mattered: vote "up" if the entity answered the need, "down" if it was wrong, irrelevant, or stale, with a short reason (e.g. "menu was current", "permanently closed"). Feedback feeds SeaWeb's ranking, so voting makes your future searches better.
| Name | Required | Description | Default |
|---|---|---|---|
| vote | Yes | ||
| reason | No | ||
| entity_id | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only indicate non-read-only and non-destructive, so the description adds useful behavioral context: feedback feeds SeaWeb's ranking and affects future searches. It doesn't contradict annotations, though it could mention whether votes are updatable or permanent.
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?
Three sentences with no fluff: the core action is front-loaded, followed by vote semantics and the consequence. Each sentence contributes essential guidance.
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?
The description covers when to call, how to vote, why it matters, and what reason to provide. For a simple 3-parameter tool with no output schema, it is nearly complete; the only minor gap is explicitly defining entity_id.
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?
With 0% schema description coverage, the description compensates by explaining the vote values ('up'/'down'), their meaning, and the reason field with an example. It implies entity_id is the search result being rated, though it doesn't explicitly spell out the identifier source.
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?
The description clearly identifies the action: rate a search result with an up/down vote. It also distinguishes itself from siblings by framing the tool as feedback for SeaWeb's ranking, which separates it from log_outcome and vote_comparison.
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 explicit timing guidance: 'Call at the end of a task for the result(s) that mattered.' It also defines when to vote up vs down. It does not mention when not to call or explicitly name alternatives, but the context is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tool clusters have fuzzy boundaries: search vs. search_restaurants/search_salons/search_web, get_entity vs. get_restaurant/get_salon/get_details, and agent_job_status vs. research_status all require careful reading to pick correctly. The long descriptions help, but the overlap is real and an agent can easily misroute a call.
Most tools follow a clean get_/list_/search_/register_/delete_ verb_noun pattern, making the bulk of the surface predictable. A few outliers like recall, remember, teamwork_preview, and travel_health break the pattern but are still readable and not chaotic.
43 tools is far beyond a well-scoped server and bundles several distinct products — vertical search, web crawl, disruption monitoring, agent memory, and A/B evaluation — into one surface. Even if each subdomain is individually reasonable, the combined count makes the server feel like multiple toolsets mashed together.
Core workflows are mostly covered: search, extract, get details, register/list/delete standing queries and webhooks, and research jobs all have usable lifecycles. However, there is no update path for standing queries or webhooks, built datasets lack a clear retrieval tool, and research jobs have status but no obvious distinct cancel/list surface.