Agora by openforallofus

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

Annotations already cover read-only and closed-world behavior. The description adds meaningful semantic context by explaining that 'operator-signed' reports mean the operator gate signed off on a call but do not prove which server answered, which helps the agent interpret returned evidence correctly.

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 definition is two tightly written sentences. The primary action and return scope are front-loaded, and the second sentence earns its place by clarifying the meaning of 'operator-signed' proof reports.

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 retrieval with annotations and no output schema, the description is complete. It identifies the resource, the exact-name requirement, the returned proof reports, and an important caveat about report interpretation.

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%, so the baseline is 3. The description adds an illustrative registry name format (io.github.owner/repo) beyond the schema's textual requirement, giving the agent a concrete example of the expected value.

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 specific verb and resource: return one MCP server from the catalog by exact registry name, along with all signed proof reports. The exact-name requirement and example format clearly separate it from the sibling search_tools, which is used to find names.

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 implies the necessary condition (you must already have the exact registry name) but does not explicitly say when to use this instead of search_tools or submit_report. Usage is inferable but not spelled out.

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 cover the safety profile (readOnly, not open-world), and the description adds genuinely useful behavior beyond them: results are ranked by match AND by signed proof reports, with 'works' lifting and 'broken'/'unsafe' demoting a server. That ranking mechanic shapes how an agent should interpret results. It stops short of describing result volume or pagination 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?

Two tight sentences, purpose front-loaded, ranking behavior second. Both sentences carry weight. Minor jargon ('signed proof reports') is used without unpacking, but there is no padding.

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?

With no output schema, the description should sketch what comes back, and it only explains ranking — not the shape of a server result or how many are returned. It is adequate for a simple search endpoint but leaves result interpretation partially to the agent.

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 only 50% — 'query' is documented but 'limit' has no description. The description never mentions either parameter, so it does not compensate for the undocumented limit or clarify query matching scope beyond the vague 'ranked by match'.

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: 'Search the catalog of MCP servers (from the official MCP registry)'. This clearly separates it from get_tool (retrieve one) and submit_report (contribute a report), though it never names those siblings explicitly and the 'servers' phrasing drifts from the tool's 'tools' name.

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?

No guidance on when to search versus calling get_tool directly, and no mention of what a good query looks like or when to stop. The description explains result ordering but not selection criteria, so usage must be inferred.

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 establish non-read-only, idempotent, non-destructive, closed-world behavior, and the description adds genuinely new context: cryptographic verification is required, the decision must be 'allow', and a record is single-use. It does not describe success/failure responses or error handling, so it adds value without being exhaustive.

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 action and the backing artifact, then the acceptance constraints. No sentence is redundant and nothing is buried.

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 mutation tool with no output schema, the definition covers the critical acceptance conditions and the crypto requirement. What remains unstated is the outcome of a submission (confirmation, storage, rejection behavior), which is a modest gap rather than a blocking 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?

Schema description coverage is only 20%, so the description must compensate, and it does for the hardest parameter: 'receipt' is characterized as a signed decision record in Cedulon format whose signature must verify under 'operatorKeyPem'. Server, verdict (enum), and note are left to the schema, which is largely self-explanatory for those fields.

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 — filing a report about a catalog server's state (works/broken/unsafe) — and immediately names the artifact that backs it (a signed decision record). This is clearly distinguishable from the read-only siblings get_tool and search_tools.

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?

Gives explicit preconditions: the record must verify under the supplied public key, its decision must be 'allow', and each record can back only one report. 'Unsigned opinions are not accepted here' rules out an obvious wrong approach. It stops short of naming an alternative tool, but no sibling performs a comparable action.

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