MCP Registry Search: find and add MCP servers

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With readOnlyHint=true already present, the description does not need to restate safety. It adds useful behavioral context by specifying what the tool returns and explaining the review-status lifecycle, which goes beyond the annotations. It does not mention error/not-found behavior, but the gap is minor for a simple read tool.

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?

Two tight sentences deliver the purpose, return contents, and usage context with no filler. The key scoping fact (exact name lookup) is front-loaded before the usage note.

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-only lookup tool with no output schema, the description sufficiently explains what the tool does, what it returns, and when to use it. Nothing an agent needs to invoke it correctly 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 100%: the single 'name' parameter is already described as an exact server name with an example. The description only restates 'exact name' without adding new parameter-level meaning, so it meets the baseline but does not exceed it.

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?

Description clearly states the action ('Get one server by its exact name') and the resource, and enumerates what is returned (manifest, review status, install snippets). This distinguishes it from search_servers, which implies broader discovery, and submit_server, which implies creation.

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 gives a clear use case: 'Use it to check on a server you submitted; status is pending until a maintainer approves it.' This provides context for when the tool is appropriate, though it does not explicitly name alternatives or state when not to use search_servers or submit_server.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, and there is no contradiction. The description adds search semantics (multi-field matching) and discloses that results are 'short summaries', so the agent knows not to expect full installation details. It does not discuss result ordering or pagination, but those are minor for a read-only registry search.

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, all substantive and front-loaded: what is searched, what is returned, and what to do next. There is no filler or repetition of schema contents.

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 an optional-parameter read-only search with no output schema, the description covers what results look like, how to get richer data, and why to use this before submit_server. Nothing needed to select it correctly 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 descriptions cover tag, query, and transport, and the description reinforces what the query can contain (free text or a tool name) by listing the fields searched. Limit and offset lack schema descriptions, but their defaults and bounds are present in the schema, so the description does not need to repeat them.

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 clear verb ('Search') and resource ('the registry for MCP servers'), and specifies the exact match surfaces ('names, titles, descriptions, tags and the names of the tools each server exposes'). It also distinguishes itself from its siblings by noting that get_server is for install instructions and search is a pre-submit duplicate 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?

Explicitly routes to get_server for install instructions and instructs to search before submit_server to avoid duplicates. This gives an agent concrete when-to-use context relative to both siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false. The description adds valuable context beyond annotations: the review-before-publication delay, error handling semantics, and the explicit prohibition on secret values. It does not contradict annotations and enriches the agent's understanding of the tool's behavior.

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, each carrying distinct and essential information: purpose, review/status behavior, and error-handling/security guidance. The description is front-loaded with the core action and remains tightly structured with no filler.

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 the tool's complexity (14 parameters, mutating action, no output schema), the description covers the critical behavioral context: the review workflow, error retry, and secret handling. It doesn't explain return values, but no output schema exists, so this is a minor gap. Overall, an agent has enough to invoke 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?

Schema description coverage is 100%, so each parameter is already well-documented. The description reinforces the env_vars rule ('names only, not values') and gives general guidance on sourcing values, but adds little that isn't in the schema. Baseline 3 is appropriate; it adds marginal value but doesn't compensate for anything missing.

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: 'Add an MCP server to the registry.' It clearly distinguishes from siblings by referencing get_server for status checking, and the purpose is unmistakable. An agent can tell this is the creation/registration tool.

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 explicit usage guidance: what to fill (from README/metadata), what to do on error (fix fields and retry), and a security constraint (env_vars names only). It also explains the post-submission review process and how to check status via get_server, covering both when and how to use it effectively.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.