explain_sendWhy one person got the simulation they got, when they got it: their security band and score, the rule that chose the lure, and the cadence that chose the moment. Answered from what was recorded at planning time, not recomputed. Use it for 'why did we phish Anna last Tuesday'.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | The person's email address, as it appears in Fallax. |
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?
The description reveals a key behavioral trait beyond annotations: the answer is 'recorded at planning time, not recomputed', meaning the explanation reflects historical state rather than live data. This is valuable context for an agent interpreting results. The annotations already declare readOnly/idempotent, and there is no contradiction.
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?
The description is two sentences: the first lists what the tool explains, the second adds the historical-source caveat and a concrete usage example. There are no wasted words, and the most important scoping is front-loaded.
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 the input context (a specific person's email via the example), the output content (band, score, rule, cadence), and the temporal caveat (recorded at planning time). With only one parameter and safe read-only annotations, nothing critical is missing for an agent to use it correctly.
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?
The schema fully documents the single parameter (email, minLength, description), so the baseline 3 applies. The description does not add additional parameter-level meaning beyond the schema's note that it is the email as it appears in Fallax.
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 states a specific verb ('explain') and a resource ('a send') and enumerates the exact dimensions of the answer: security band and score, the rule that chose the lure, and the cadence that chose the moment. It clearly distinguishes the tool's purpose from siblings like get_campaign or get_breakdowns by focusing on the 'why' and 'when' for a single person.
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?
The description provides a concrete use case: 'Use it for "why did we phish Anna last Tuesday".' This gives clear context for when to invoke it. It does not explicitly name alternative tools or exclusions, so it stops short of the highest bar for usage guidance.
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.
Most tools have distinct purposes, but get_programme_status and get_setup_status both report whether the continuous programme is running, and get_program_summary, get_breakdowns, and get_resilience_trend all expose similar rate metrics. Descriptions help clarify the differences, but an agent could still pick the wrong reporting tool for a given question.
All names use a predictable lowercase snake_case verb_noun style with get_, list_, exclude_, pause_, and explain_. The main inconsistency is the program/programme spelling difference between get_program_summary and get_programme_status, and explain_send is a slightly less conventional noun.
12 tools is a well-scoped size for a phishing-simulation insight and safety-control server. Each tool covers a distinct reporting angle or operational action without feeling padded.
The read and analytics surface is thorough, covering summaries, breakdowns, trends, evidence, setup, and individual explanations. However, the operational side is one-directional: exclude_person and pause_programme have no include or resume counterpart, and there is no campaign or person management tooling, leaving explicit dead ends.