Get usage metrics for this server session: calls, latency, errors, payload size.
Per tool: call count, p50/p95/max latency, average and peak response size,
and how many responses exceeded the payload budget. Plus cache hit rate and
a breakdown of errors by type.
Counters are per-process and reset when the client restarts the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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?
There are no annotations, so the description carries the behavioral transparency burden. It discloses realistic behavioral details: counters are per-process, reset when the client restarts the server, and the stats include cache hit rate and error breakdowns. This goes well beyond a generic 'retrieve stats' phrasing.
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 tight and well structured: one summary line, one detailed breakdown, and one line about reset behavior. Every sentence earns its place, with no filler or redundant restatement of the tool name.
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?
Given there is no output schema, the description provides enough context by enumerating the metric categories, the per-tool granularity, and the reset lifecycle. With no parameters, there are no missing input-related details, and the expected result is adequately characterized.
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 tool has zero parameters and 100% schema description coverage, so the description does not need to explain inputs. It correctly focuses on what the returned metrics mean, which is the only relevant semantic content for a no-argument tool.
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 opens with a specific verb and resource: 'Get usage metrics for this server session,' then enumerates exact metric categories (calls, latency, errors, payload size). This is unambiguous and clearly distinguishable from sibling tools, including the similarly operational-looking health_check.
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 intended use is implied by the phrase 'Get usage metrics for this server session,' so an agent can infer when to call it. However, the description provides no explicit when-to-use/when-not-to-use guidance and does not contrast itself with siblings like health_check or other monitoring tools.
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.
Every tool targets a distinct astrological subsystem — positions, houses, aspects, strengths, dashas, transits, yogas, doshas, vargas, karakas, etc. The pairs that could plausibly be confused (calculate_birth_star vs create_chart, get_current_dasha vs get_dasha_periods, get_timeline vs get_transits) are explicitly cross-referenced with guidance on when to use which, so an agent can disambiguate reliably.
24 of 30 tools follow a uniform get_X pattern, and the remaining action tools (create_chart, calculate_birth_star, describe_chart, rectify_birth_time) still use verb_noun. Only health_check and server_stats break the pattern as noun-style names, and the different verbs reflect genuinely different actions rather than inconsistency.
30 tools is on the heavy side and exceeds the comfortable range, even though Vedic astrology is a genuinely broad domain with many distinct subsystems. Some tools are meta or adjacent (get_account_status, health_check, server_stats, get_prompt_library, get_numerology) and a couple could arguably be consolidated (get_current_dasha as a mode of get_dasha_periods), but each tool does carve out a distinct purpose.
The chart lifecycle is fully covered: create_chart produces a cached handle, describe_chart inventories it, and the get_* readers retrieve every section. Timing (dashas, transits, timeline), strengths (shadbala, vimsopaka), yogas, doshas, vargas, compatibility, rectification, and even meta-concerns (account status, health) are all present with no obvious dead ends or missing operations for a computation-cache domain.