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

Annotations already declare readOnly, idempotent, and non-destructive, so safety is covered. The description adds genuinely useful behavioral context beyond that: only heads are exposed and local Git state must be supplied by the agent, which prevents an agent from assuming it can resolve local refs.

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 short sentences, front-loaded with the core capability, then two constraints. Every sentence earns its place 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?

With no output schema and 7 parameters, the description covers the important gotchas (case-sensitive names, heads-only scope, no local state). Pagination is handled by the schema's top/continuationToken descriptions, so nothing critical is left for the description to carry.

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 86%, so the schema already documents top, branch, prefix, project, repository, and continuationToken. The description's case-sensitivity note is relevant to the branch parameter, but otherwise adds little beyond the structured fields, which is the expected baseline.

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 verb pair (get/list) and resource (remote Git branch), so an agent immediately knows this reads branch data. The resource is clearly distinct from the PR/repository siblings, but it never explicitly differentiates itself from them, keeping it just short of a 5.

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 phrasing 'get an exact branch or list branches' implies the two modes and the schema's action enum plus branch/prefix descriptions fill in the conditions. There is no explicit when-to-use/when-not guidance against alternatives such as repo_repository, so usage is only implied.

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, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds one useful behavioral detail — that results include human-facing PR URLs — but says nothing about pagination behavior or auth/permission requirements, which is the kind of context that would raise this above baseline.

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 with the primary read operations front-loaded and the filter/return details trailing. No filler and nothing that could be cut without losing 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?

For a 9-parameter read tool with no output schema, the description covers both operation modes, the filters, and the nature of the return value (PR URLs). It is close to complete, missing only pagination/return-shape detail and explicit sibling routing, which are minor given the annotation coverage.

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 78% with 9 parameters, and the schema already documents top, skip (including nextSkip), project, repository, branches and pullRequestId. The description only echoes the status and branch filters, adding no syntax or format meaning beyond the structured fields, 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 specific verbs and resource: 'Get a pull request by ID or list pull requests in a repository,' plus the optional filters. It clearly separates the two modes, but it never names or contrasts with the sibling repo_pull_request_write, leaving the read-vs-write routing to inference from the tool 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?

It implies usage by pairing 'get' with an ID and 'list' with a repository, and notes the available filters, but gives no explicit when-to-use/when-not guidance, no mention of the write sibling as the alternative for mutations, and no prerequisites such as the ADO_PROJECT default.

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?

Goes well beyond the annotations by disclosing that writes are disabled unless a process-configured ADO_ALLOWED_REPOSITORIES entry exists, enumerating the unsupported operations, stating the input the agent must supply, and prescribing behavior after an ambiguous write outcome. This is exactly the kind of mutation-side context the hints (destructive=false read profile) cannot convey.

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: primary action first, then permission gate, then scope limits, then recovery. Each sentence carries distinct operational information 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?

For a write tool with no output schema, the description covers authorization, scope limits, prerequisites, and failure handling, leaving only the returned value (e.g., the new PR identifier needed for follow-up calls) unmentioned.

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 already 89%, so parameter meaning is largely carried by the schema itself; the description's mention of project/repository and local Git context adds little. The 'verify both remote branches' remark loosely reinforces sourceBranch/targetBranch semantics but no format or constraint detail is added.

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 specific verbs and resource ('Create a PR ... or update its title, description, or draft state'), covering both action modes the enum supports. The explicit exclusion list (no merge, completion, autocomplete, policy bypass, retargeting, or branch deletion) draws a clean boundary against other PR-related operations.

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 clear preconditions ('after verifying both remote branches'), an authorization gate (ADO_ALLOWED_REPOSITORIES), and a recovery path ('After an uncertain write outcome, list PRs before retrying'). It does not name the sibling tool (repo_pull_request) that performs that listing, so routing is implied rather than explicit.

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, idempotent, non-destructive, openWorld), so the bar is lower. The description still adds real behavioral context beyond them: an ADO_ALLOWED_REPOSITORIES allow-list silently restricts both results and access, which an agent must know before interpreting an empty list as 'no repositories exist.'

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 short sentences, front-loaded with the core purpose, then the allow-list caveat, then the prerequisite. Every sentence carries distinct information and none of it is 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?

For a read-only lookup/list with no output schema, the description is nearly complete: it covers scope, accepted identifier forms, and the access restriction. It could mention returns (id/name/URL) or that paging uses skip, but the schema's nextSkip note largely covers pagination, leaving only a minor gap.

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 80%, so the schema already documents top, skip, project, and repository. The description repeats that 'names and IDs are accepted,' which is largely redundant with the schema's 'Project name or ID' phrasing, and adds nothing about the action enum. Baseline 3 is appropriate since the schema does the heavy lifting.

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 ('Get or list Git repositories') and the scope ('in an Azure DevOps Server project'), with the get-vs-list duality matching the action enum. The resource is unambiguous against siblings like repo_branch and repo_pull_request, which operate on entirely different entities.

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?

Provides an explicit prerequisite: 'Use server_info/list_projects first if the project is unknown.' This is clear context for when the caller lacks a project identifier, but it offers no exclusions or alternatives among the sibling repo tools for cases like resolving a branch or PR.

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/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds genuine value beyond them: the repository allowlist narrows both diagnostics and discovery scope, credentials are never returned, the API version is fixed by configuration, and product build is reported only when the server supplies it. Auth requirements and error behavior are still unstated.

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 sentences, front-loaded with the two primary modes before the scoping and security caveats. Every sentence carries information; the allowlist sentence is slightly dense but not redundant.

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?

No output schema exists, so the description must carry return-value expectations — and it does, by stating credentials are never returned and build is conditional. With three optional params and full annotation coverage, only auth/permission prerequisites are 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 67%: top and continuationToken carry their own descriptions, while action has only an enum with no explanation. The description's two modes implicitly explain what action=get vs list_projects do, but it adds no format or pagination detail, so this sits at the baseline.

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 two concrete operations — connectivity/safe-configuration diagnostics and discovery of accessible projects — which maps cleanly onto the get/list_projects enum. It is clearly a server-level tool, distinct in domain from the repo_* siblings, though it never names or contrasts an alternative explicitly.

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?

It gives a real trigger condition: use discovery 'without a configured default project', and use diagnostics to check connectivity/safe configuration. No exclusions or named alternatives are offered, so it stops short of a 5.

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