Epovest

Check a corroboration against its page, now

verify_corroboration

Idempotent

Read the page again and report what it says today. One pass returns two findings, dated, and included at no cost. On the MENTION: the passage around the brand is archived on the line (the sentence that names it, one before, one after), and the finding says unchanged, changed (the passage moved, worth re-reading), figures (the passage moved on NUMBERS only, such as a rank or a counter: a fact to read, and changed_at stays where it was) or gone (the page did not answer). When a change was found, excerpt_before carries the passage as it stood BEFORE changed_at: compare it with excerpt to state what moved, in words, without reading the whole page. On the LINK: every link of the page towards an address of the brand, derived from the canon website and from the surface registry of the project, with its rel tokens (nofollow, sponsored, ugc, or none), its target and title attributes, its anchor text, its exact destination with the resolved redirect chain and the HTTP code of that destination, whether it sits in the main content or outside it, and its dates; the finding says unchanged, changed (changes lists what moved: rel, anchor, target, placement, appeared), gone, or none, which means the page carries no such link and is a normal state. The reply also carries how the page reads (readability: "html" when it reads, "blocked" when an anti-bot stands in front of it, "unreachable" when it did not answer, "no_page" when the address answers with something that is not a page, "unreadable" when it answers HTML with no text in it, "pending" while no reading has completed yet), the number of outbound links of the page, and what the page declares about itself (noindex, page_nofollow, canonical_elsewhere). Read readability before deciding a move: an anti-bot is a fact of the world, while a page that did not answer is worth reading again. Everything here is a FACT: the third party has the final say, so nothing closes, nothing counts, and nothing is taken down on its own. Use it to decide a move, then record the outcome in the logbook.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`corroboration_id`	Yes	The UUID of the corroboration: call list_corroborations to find it.

TDQS

A4.4/5.0

Behavior5/5

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

The description extensively discloses return formats (findings for MENTION/LINK, readability states, outbound link count) and emphasizes non-destructiveness: 'nothing closes, nothing counts, and nothing is taken down on its own.' This adds significant context beyond the sparse annotations and does not contradict them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long and dense but every sentence provides needed detail. It could be better structured with bullets, but it is not verbose or repetitive.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description thoroughly explains all return values (e.g., finding types, readability states, link attributes) and edge cases. It is exceptionally complete for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema fully describes the only parameter (corroboration_id with instruction to use list_corroborations). The description adds no extra parameter details, but baseline 3 applies due to 100% schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The title 'Check a corroboration against its page, now' and description 'Read the page again and report what it says today' clearly state a specific verb and resource. It distinguishes itself from sibling tools like archive_corroboration or update_corroboration by focusing on re-reading the page for verification.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit context: 'Use it to decide a move, then record the outcome in the logbook' and advises reading readability before acting. It does not name alternatives, but the use case is clear enough.

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

All Epovest tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0

Disambiguation4/5

Each tool maps to a distinct resource and action, and the descriptions go out of their way to separate near-neighbor concepts like surfaces vs corroborations and score series vs raw responses. A few related pairs (get_results/get_responses, get_credits/get_usage, create_surface/create_corroboration) could still be confused at a glance, so it is not a perfect 5.

Naming Consistency5/5

Tool names follow a highly consistent verb_noun snake_case pattern across all 67 tools, with clear families like create_, update_, get_, list_, archive_, restore_, and delete_. Minor quirks such as topup_credits as one word do not break the overall uniformity.

Tool Count1/5

67 tools is an extreme count for a single MCP server, even for a broad brand-monitoring domain. The surface is bloated with lifecycle variants per entity, and the sheer number makes the server hard to navigate and prompt against.

Completeness5/5

The server covers full lifecycles for projects, trackers, surfaces, corroborations, quests, logbook entries, keyword discoveries, competitor scans, link targets, sources, support, and billing. Archive/restore and soft-delete paths prevent dead ends, and nearly every obvious workflow has a corresponding tool.

Resources

Need Help?