An employer's Pay Transparency Score: the percentage of its active postings that state pay, computed weekly from its own public career board. Includes posting counts and advertised ranges by role. Scores cannot be bought.
| Name | Required | Description | Default |
|---|---|---|---|
| employer | Yes | Employer name, e.g. 'Mount Sinai' |
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 provided, the description carries the full burden of behavioral disclosure. It reveals the metric formula, the weekly computation cadence, the data source, and the included output details such as posting counts and ranges by role. It also adds a trust-related guarantee that scores cannot be bought, which is more transparency than expected.
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 compact and well structured: the first sentence defines the core metric, the second lists what is included, and the third offers a meaningful guarantee. Every sentence contributes non-redundant information and the main definition 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?
For a simple one-parameter read-only tool with no output schema, the description is largely complete: it states the metric, source, update frequency, and return contents. An agent can correctly select and invoke the tool using only the employer name from the schema. Minor details such as not-found behavior are not specified, but this does not seriously impair usability.
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 single parameter, employer, is fully documented in the schema with a description and example, giving 100% schema description coverage. The tool description adds no significant parameter-level detail beyond tying the score to an employer, which is adequate under the baseline rule.
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 clearly identifies the resource and computation: an employer's Pay Transparency Score defined as the percentage of active postings that state pay, sourced from the employer's own public career board. It also distinguishes itself from sibling tools like get_pay_range and check_offer by focusing on an employer-level score rather than individual offers or ranges.
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 explains what the tool provides and how the score is computed, so an agent can infer when it is relevant. However, it never explicitly states when to prefer this tool over siblings or when not to use it. No alternatives or exclusion conditions are mentioned.
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 targets a distinct operation: comparing an offer, retrieving a pay range, getting an employer score, and listing employers. There is mild overlap between check_offer and get_pay_range, but their purposes are clearly separated by whether a specific offer is being evaluated.
All tool names follow the same verb_noun pattern: check_offer, get_employer_score, get_pay_range, list_employers. The naming is predictable and makes the action and target of each tool immediately clear.
Four tools is a well-scoped count for this focused domain. Each tool covers a meaningful interaction with the pay transparency dataset without redundancy or unnecessary surface area.
The set covers the core workflows: viewing pay ranges, checking an offer, seeing an employer's transparency score, and browsing tracked employers. Minor gaps exist, such as no dedicated employer detail view or filtering/searching, but agents can accomplish the main jobs without dead ends.