Skip to main content
Glama

Boosthis

by com.boosthis

Session Summary

boosthis_session_summary
Read-only

Per-screen p50/p75/p95 and worst rating, worst screens first, with p99, spike ratio and stdev spread where the server has them. Without read credentials: a note pointing at the dashboard, never empty. Read-only. More projects: your_projects; a shared project_group is one project in several runtimes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
projectNoProject to read: dashboard name, 'name (runtime)' or install id; needs account_token, else the newest reporter.
install_idNoInstall id (dashboard card).
read_tokenNoRead-only token, same card.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed2 schema fields changed
    • changedInput schema / properties / install_id / description
      Previous value: -"Install id, from the dashboard card."New value: +"Install id (dashboard card)."
    • changedInput schema / properties / project / description
      Previous value: -"Project to read: dashboard name, 'name (runtime)', or install id. Needs account_token; absent, the most recent reporter."New value: +"Project to read: dashboard name, 'name (runtime)' or install id; needs account_token, else the newest reporter."
  2. Changed2 schema fields changed
    • changedInput schema / properties / install_id / description
      Previous value: -"Install id, from the project's dashboard card."New value: +"Install id, from the dashboard card."
    • changedInput schema / properties / read_token / description
      Previous value: -"Read-only token for it, from the same card."New value: +"Read-only token, same card."
  3. Changed3 schema fields changed
    • changedInput schema / properties / install_id / description
      Previous value: -"Optional: the install id to read live data for. On the HOSTED Boosthis MCP, copy it from the in-app dashboard's \"Connect your AI\" card and pass it here. Omit on a local stdio server (it uses BOOSTHIS_INSTALL_ID from the env)."New value: +"Install id, from the project's dashboard card."
    • changedInput schema / properties / project / description
      Previous value: -"Which project in the account to read — its dashboard name, that name with a runtime as 'name (runtime)', or an install id. Only meaningful with account_token."New value: +"Project to read: dashboard name, 'name (runtime)', or install id. Needs account_token; absent, the most recent reporter."
    • changedInput schema / properties / read_token / description
      Previous value: -"Optional: the SELF-scoped read token for that install (paired with install_id). It is read-only — it can read this app's own perf data but CANNOT delete it. Copy it from the in-app dashboard. Omit on a local stdio server (it uses BOOSTHIS_READ_TOKEN from the env)."New value: +"Read-only token for it, from the same card."
  4. Changed1 schema field changed
    • changedInput schema / properties / project / description
      Previous value: -"Which project in the account to read — its name as shown on the Boosthis dashboard (for example 'Rival Web'), a specific runtime of it as 'name (runtime)', or an install id. A project measured in several runtimes answers with its most recent one and names the others in `your_projects`. Only meaningful with account_token; absent, the answer is whichever project reported most recently."New value: +"Which project in the account to read — its dashboard name, that name with a runtime as 'name (runtime)', or an install id. Only meaningful with account_token."
  5. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Goes beyond the annotations by disclosing the worst-first ordering, conditional metric availability ('where the server has them'), and the degraded-mode fallback ('Without read credentials: a note pointing at the dashboard, never empty'). The 'Read-only' sentence merely repeats readOnlyHint=true and earns no credit. The fallback note's contents are underspecified, but the disclosed traits are genuinely useful.

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?

Three dense sentences, front-loaded with the output spec and ordering, with no background or marketing prose. The only real waste is the redundant 'Read-only' clause, and the project_group note is slightly tangential though useful.

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

Completeness4/5

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

For a tool with three optional parameters and no output schema, the description covers output content, ordering, degraded mode, and ambiguous project grouping. Remaining gaps — the response shape and units, and what 'worst rating' means — are minor, though the absent output schema raises the bar slightly.

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 description coverage is 100%, so the baseline is 3; the description adds value above it by tying read_token to a concrete behavior (the dashboard-note fallback) and by clarifying project-group semantics for the project parameter. These are additions, not repetitions of the schema.

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

Purpose4/5

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

The description specifies the exact output content: per-screen p50/p75/p95, worst rating, worst screens first, with p99, spike ratio and stdev spread where the server has them. This specificity distinguishes it from siblings like boosthis_trend, boosthis_recent_samples and boosthis_snapshot. The verb is implicit (nothing literally says 'returns' or 'summarizes'), which keeps it just below a 5.

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

Usage Guidelines3/5

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

Usage context is implied rather than stated: the metric list tells an agent what kind of data to expect, but there is no explicit when-to-use guidance, no exclusions, and no alternative routing to a named sibling. The one sibling mentioned, `your_projects`, appears only for project semantics ('a shared project_group is one project in several runtimes'), not as a preference rule for other cases.

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

All Boosthis toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation4/5

Most tools target a distinct resource or workflow: alerts, budgets, crashes, traces, jobs, promises, kits, and rules. A few summary-style tools such as snapshot, session_summary, and what_should_i_look_at_next overlap in spirit, but their descriptions clarify the different aggregation levels and purposes.

Naming Consistency4/5

All tools share the consistent boosthis_ snake_case prefix, making the family immediately recognizable and predictable. However, naming mixes noun-resource styles with verb-command styles, and a few names are question-like phrases such as boosthis_what_should_i_look_at_next and boosthis_which_kits.

Tool Count3/5

At 26 tools, this is on the heavy side and slightly past the 16-25 range where a large toolset starts to feel burdensome. The count is defensible because each tool maps to a distinct observability or kit-management concern, but agents will need to do significant selection work.

Completeness4/5

The surface covers a broad lifecycle: kit installation and verification, rules and code matching, performance snapshots and trends, crash risk, release checks, promises, alerts, and connection status. It is mostly read-only by design, so the lack of write operations beyond remember_promise is not a major gap, though alert and job management actions are intentionally absent.

Resources