Where apps write their log files on Windows, macOS and Linux, as exact copyable paths.
Scored across 2 tools
search_log_locations is for discovery by app name/alias/file, while get_app_log_locations retrieves details for a known slug. The two are related and both return log locations, which could cause slight confusion, but the slug requirement makes the intended workflow clear.
Both names follow a consistent snake_case verb_noun pattern and share the _log_locations suffix. The difference between get_ and search_ is a standard and predictable distinction.
Two tools is borderline thin for a server, though the narrow lookup purpose could justify it. The surface may feel under-scoped compared to typical MCP servers with more operations.
The search-then-get workflow covers the main lifecycle for finding log locations. Minor gaps exist, such as no obvious way to list all apps without a search term or to reverse-lookup an app from a known log path.
Every log location for one app, by the slug that search_log_locations returns.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds only a mild behavioral claim ('Every' suggests an exhaustive, unpaginated result set) and says nothing about result size, limits, or error behavior for an unknown slug.
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?
A single sentence with no waste, front-loading the resource and scope before the input provenance. Every clause earns its place.
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?
For a one-parameter read tool with annotations and no output schema, the description covers purpose, scope, and input provenance. It could say a bit more about the returned location shape or behavior for an invalid slug, but nothing essential to correct invocation is missing.
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?
Schema coverage is 0%, so the description carries the burden, and it does supply the key semantic: the slug is the identifier returned by search_log_locations. It does not describe the slug format or an example, but the provenance is the most important missing piece and it is provided.
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 precise resource and scope ('Every log location for one app'), which is more than a restatement of the title, and it names the sibling search_log_locations as the upstream source of the slug. Differentiation from that sibling is present but implicit rather than spelled out.
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 makes the workflow dependency clear: the slug comes from search_log_locations, so an agent knows this is the drill-down step after a search. There is no explicit when-not guidance or statement of an alternative path, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find where an application writes its log files. Matches app names and aliases (for example 'teams', 'zoom', 'docker') and the names of files listed under a path (for example 'AppWorkload.log'), not vendor names. Returns each app's log paths by platform.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | App name or alias | |
| platform | No | Only paths on this platform |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful matching semantics beyond the annotations: aliases are matched, file names under paths are matched, vendor names are NOT matched, and results are grouped by platform. It doesn't cover result ordering or truncation behavior when limit is hit, which is a minor gap.
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, front-loaded with the purpose, then matching rules, then output shape. No filler and no repetition of the title.
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?
For a read-only search tool with no output schema, the description tells the agent what it matches, what it excludes, and the shape of the return (log paths per app, per platform). The only unaddressed items are the limit parameter's truncation behavior and any ordering guarantee, which are minor.
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?
Schema coverage is 67%. The description adds real meaning beyond the schema: 'query' accepts app names AND aliases AND file names like 'AppWorkload.log' but NOT vendor names, and results are returned per-platform (linking to the 'platform' param). 'limit' semantics remain undocumented in both places, so not a 5.
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 resource ('Find where an application writes its log files') and immediately scopes what is and isn't matched (app names/aliases and file names, not vendor names). This distinguishes it from the sibling get_app_log_locations, which is a direct-lookup rather than a search.
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?
Usage is implied by 'Search' and by the query-matching rules, so an agent knows this is the discovery path when it has only a fuzzy name. However, no explicit when-to-use vs get_app_log_locations guidance is given, so the agent must infer that it should prefer this for partial/ambiguous names and the sibling for exact lookups.
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.
get_app_log_locationssearch_log_locationsOpen-source agent that observes and fixes your application. Query logs, traces, metrics, incidents.
Changelogs for apps, games and operating systems. Ask what shipped since the version you run.
Read-only access to Auralogs production logs: search logs, inspect errors, review AI analyses.
Verified, version-pinned records of new dependency bugs: look an error up before searching the web.
Add one secure layer between your agents and this server.
