Weekly client reports: change, % change, targets, status, printable page and email text. Free.
Scored across 1 tool
There is only one tool, so there is no possibility of tool-to-tool confusion or misselection. Its trigger conditions (weekly/monthly/campaign reports, KPI updates) are clearly stated.
The single name 'build_client_report' follows a clean verb_noun snake_case convention. With only one tool there is nothing to be inconsistent with.
A single tool is thin, but the domain (generating a formatted client report from metrics) is narrow enough that one comprehensive tool is defensible. It sits at the borderline of the 1-2 tool range.
Generation is well covered (computed deltas, formatted report, email text, printable link), but the lifecycle is one-way: there is no way to list or retrieve previously generated reports, store metrics history, or update/regenerate an existing report.
Use this when the user wants to write, build or format a weekly, monthly or campaign report for a client or boss ("weekly client report", "status report", "monthly marketing report", "KPI update", "Friday report"). Pass each metric with its current and previous value (and target, if any); the tool computes changes, % change, target status and an overall status, and returns a formatted report, email-ready text and a printable link (Save as PDF). Do not invent numbers: ask the user for any metric values you do not have.
| Name | Required | Description | Default |
|---|---|---|---|
| wins | No | ||
| client | Yes | Client or project name | |
| issues | No | Blockers or risks | |
| period | No | e.g. "Week of 6 Oct 2026" or "September 2026" | |
| metrics | Yes | ||
| summary | No | One or two sentences in the user's words (optional) | |
| nextSteps | No | ||
| preparedBy | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare the safety profile (read-only, idempotent, non-destructive, closed-world). The description goes well beyond that by disclosing the computation performed (changes, % change, target status, overall status) and the exact return artifacts (formatted report, email-ready text, printable/PDF link), plus a data-integrity rule about prompting the user for missing numbers.
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?
Front-loads the use case and keeps to three sentences with no filler. The parenthetical trigger-phrase list is long but earns its place by enabling intent matching; the only mild cost is density.
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?
With no output schema, the description correctly explains the return artifacts, and it documents the metric inputs and the no-fabrication guardrail. The gap is the unmentioned optional fields (wins, issues, nextSteps, preparedBy) that have no schema descriptions either, so an agent gets no explicit guidance on them.
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 50% schema coverage and no output schema, the description carries real weight: it specifies the metric contract (current + previous, target optional) and ties those inputs to the derived outputs, which the schema does not express. It is silent on higherIsBetter, period, wins, issues, nextSteps and preparedBy, so the semantics are not fully covered.
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?
States a specific verb and artifact (write/build/format a weekly, monthly or campaign client report) and enumerates the exact user phrasings that should route here. It is immediately clear what the tool produces and what situation it serves, with no siblings that could be confused with it.
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?
Opens with a direct conditional ('Use this when the user wants to ...') and lists concrete trigger utterances. It also supplies a genuine when-not constraint in spirit: 'Do not invent numbers: ask the user for any metric values you do not have.' No alternatives exist, so no sibling routing is needed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
build_client_report3 fields changedInput schema / properties / client / descriptionAdded value: +"Client or project name"Input schema / properties / client / examplesAdded value: +[
+ "Acme Co"
+]Input schema / properties / metrics / examplesAdded value: +[
+ [
+ {
+ "current": 86,
+ "name": "Leads",
+ "previous": 71,
+ "target": 90
+ }
+ ]
+]build_client_reportWeekly client reports: accomplishments, hours, blockers. Free.
Client, workout, body composition, retention and finance management for personal trainers.
Free for restaurant owners. Drop last night's close, get the one thing to fix before next shift.
Track workouts, nutrition, body metrics, habits, and SMART goals with insights and trends. Connect…
Add one secure layer between your agents and this server.