GitDiagram

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuine behavioral detail beyond them: substring matching semantics against "owner/repo", a 10-result cap, most-starred-first ordering, and the fact that each hit carries an interactive diagram link.

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?

Four front-loaded sentences with no filler: purpose, matching semantics with examples, use cases, and the scope limitation. Each sentence contributes distinct information and the ordering puts the core capability first.

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 two-parameter, no-output-schema search tool, the description covers purpose, matching semantics, ordering, result cap, returned artifact, and scope exclusions. Nothing an agent needs to invoke it correctly or interpret results 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 description coverage is 100%, so the baseline is 3, but the description adds matching behavior the schema does not state clearly: that any part of "owner/repo" is matched, with concrete example fragments ("langchain", "vercel/", "react-native"). The limit parameter's default and range are left to the schema, which handles 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 specific verb (Search) and resource (GitDiagram's library of architecture diagrams for public GitHub repos), with the searchable field (owner or repository name) made explicit. It is clearly distinguishable from siblings like get_repository_diagram, which fetches one diagram rather than searching.

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 two concrete use cases (resolving a project name to its exact owner/repo, and listing repos of an owner or topic that already have diagrams) plus an explicit exclusion: it searches names only, not code or file contents. It stops short of naming the sibling tool to use for retrieval, so it is clear but not fully routing.

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 readOnly=true, idempotent=true, destructive=false, so the safety profile is covered. The description adds meaningful behavior beyond that: it enumerates the returned content (link, title, length, transcript) and discloses the negative case ('when none exists it says so and links the page where one can be made'), which is genuinely useful failure-path context.

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 purpose is front-loaded and each clause carries information (what it returns, when to use it, its read-only nature, the no-video fallback). It is a dense single paragraph that runs slightly long, but there is no filler sentence to cut.

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?

There is no output schema, so the description carries the return-value burden and does so by naming the link, title, length and transcript. Combined with the explicit negative case and the covered safety annotations, an agent has everything needed to call this 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% and the single 'repository' parameter already documents both the owner/repo form and accepted github.com URLs. The description adds no format or syntax detail beyond the schema, so the baseline 3 applies.

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 ('Get'), a specific resource ('GitDiagram's narrated explainer video of a public GitHub repository'), and the conditional nature of the result ('if one has been made'). It is clearly distinguishable from the diagram-related siblings find_repository_diagrams and get_repository_diagram.

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 when-to-use triggers: the user wants a video, something to watch or share 'instead of read', or a spoken-style summary. The 'instead of read' phrasing implicitly routes away from the diagram siblings, but it never names them, so the alternative selection isn't fully 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 declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavior: it returns a pre-generated diagram rather than generating one ('fast'), returns a make-on-open link when none exists, is limited to public repos, and renders a zoomable interactive view in chat apps. It omits any auth/rate-limit context, but for a public read tool the added behavioral detail is solid.

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 front-loaded with the core purpose and return contents, then layers on usage triggers, constraints, and the interactive-view detail. It is on the long side and a couple of clauses could be trimmed, but every sentence carries substantive information.

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 one required parameter, no output schema, and annotations covering the safety profile, the description fills the remaining gap by detailing what the response contains and what happens on the not-yet-generated path. An agent has everything needed to call it and interpret the result.

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% and the single 'repository' parameter's accepted formats (owner/repo or any github.com URL) are fully documented in the schema itself. The description adds no parameter-specific syntax or format guidance, so the baseline 3 applies.

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 ('Get the architecture of a public GitHub repository from GitDiagram') and enumerates exactly what is returned: written explanation, components with source paths, connections, and a Mermaid flowchart. It is very clear what the tool does, though it never names or contrasts itself with the sibling find_repository_diagrams, so it stops short of full sibling differentiation.

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 context is stated richly: 'Use it whenever the user wants to understand, visualize, map or explain a GitHub repository's ... architecture' and 'wants an overview before reading unfamiliar code.' It also states a boundary ('Public repositories only') and a fallback path when no diagram exists. It does not, however, name an alternative tool or say when NOT to use this one versus find_repository_diagrams.

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