How many live museum and curatorial postings state a salary, and the median advertised figure among those that do -- the CuratorSearch Curatorial Pay Archive headline number, computed live.
| 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?
With no annotations, the description carries the full burden. It does disclose that the figure is 'computed live' and specifies the exact output values (count and median). However, it does not mention read-only status, data freshness caveats, authentication requirements, or any limitations, leaving some behavioral context undisclosed.
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 a single sentence that packs in the core output, the population of postings, and the live-computation trait with no filler. It is front-loaded with the headline question and remains readable despite the appended archive-name clause.
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 parameterless aggregate, the description adequately covers what is computed and the output values. The only minor gap is that it does not state whether the result is a formatted string, a single number, or a structured object, but the absence of an output schema makes this a small omission rather than a critical one.
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, so the empty schema is fully complete. The description adds no parameter-level detail, but none is needed; the baseline of 4 applies because there is nothing for the description to compensate for.
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 names a specific metric (count of live postings with salary and median advertised salary) and a specific resource (the CuratorSearch Curatorial Pay Archive headline number). This is clearly distinct from sibling tools like get_job, institution_jobs, and search_jobs, which retrieve individual or filtered job data rather than aggregate pay statistics.
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?
There is no explicit guidance on when to use this tool versus the sibling tools. An agent must infer from the aggregate nature of the description that this is for headline pay statistics rather than job lookup or search, but no when-to-use or when-not-to-use conditions are stated.
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.
Each tool serves a distinct function: get_job fetches a single job by slug, search_jobs queries listings, institution_jobs filters by institution, and salary_transparency provides aggregate pay statistics. There is no overlap in purpose, so an agent can easily choose the right tool.
All names are snake_case and descriptive, but they mix verb-first (get_job, search_jobs) with noun-first (institution_jobs, salary_transparency) patterns. The convention is not perfectly uniform, but the names remain intuitive and readable.
With 4 tools, the server is tightly scoped to its job-search purpose. Each tool addresses a distinct need—search, detail, institution-specific, and aggregate statistics—without redundancy or bloat.
The core workflows (searching, retrieving details, and filtering by institution) are covered, and the salary transparency tool adds a valuable analytical feature. A minor gap is the absence of a way to list all institutions without knowing a name upfront, but this does not significantly hinder typical usage.